© 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. 99926
    Prev
    Next
    INDEX
    Explanations

    login, register, post, password actions

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

    The neuron is looking for string literals that specify URL paths or route names (e.g. “/login”, “admin/login”, 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
    -0.94
    紘
    -0.92
     поки
    -0.82
     eliminado
    -0.79
    Deacti
    -0.76
    Editar
    -0.76
     használat
    -0.76
     ribuan
    -0.74
    コス
    -0.74
    lsz
    -0.73
    POSITIVE LOGITS
     processing
    1.90
     process
    1.83
     submit
    1.73
     processed
    1.59
    process
    1.58
    提交
    1.45
    submit
    1.45
    Submit
    1.44
    PostMapping
    1.43
    Process
    1.41
    Activations Density 0.009%

    No Known Activations