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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49734
    Prev
    Next
    INDEX
    Explanations

    login page, service, attempts

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

    The neuron strongly responds to occurrences of the token “login.”

    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
    0
    -1.00
    ベット
    -0.92
     Notwithstanding
    -0.92
    蜍
    -0.91
    esper
    -0.89
     greyish
    -0.89
    がる
    -0.86
     队
    -0.86
     وصف
    -0.85
    袴
    -0.85
    POSITIVE LOGITS
     attempts
    1.16
    attempts
    1.09
     almas
    1.06
     帅气
    1.06
     simmer
    1.03
    ၄
    1.02
     bocas
    0.99
    hésite
    0.99
    活躍
    0.96
     áreas
    0.96
    Activations Density 0.010%

    No Known Activations