© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55992
    Prev
    Next
    INDEX
    Explanations

    login and registration

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is activated by high-frequency function words and punctuation (common short tokens like commas, “and,” “to,” “on,” “/,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LoginActivity
    -1.78
    LoginComponent
    -1.72
     LoginComponent
    -1.68
    LogIn
    -1.63
    LoginPage
    -1.55
    loginPage
    -1.55
     LoginPage
    -1.52
    logIn
    -1.41
    SignIn
    -1.37
    userLogin
    -1.37
    POSITIVE LOGITS
     profile
    1.29
    Profile
    1.24
     protected
    1.21
     after
    1.16
    profile
    1.13
     private
    1.06
     Profile
    1.05
     dashboard
    1.05
    protected
    1.05
    dashboard
    1.04
    Activations Density 0.045%

    No Known Activations