© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 83371
    Prev
    Next
    INDEX
    Explanations

    if or because

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

    prevent or discourage actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recruiter
    0.47
    ുണ്ട
    0.43
     unofficial
    0.43
    PlayerData
    0.42
     isAdmin
    0.41
    दाताओं
    0.41
    resourceUrl
    0.41
    ፏ
    0.41
     Inequality
    0.41
     agenda
    0.40
    POSITIVE LOGITS
     porque
    0.54
     kalau
    0.53
     если
    0.51
     إذا
    0.51
     که
    0.49
     jika
    0.49
     susceptibles
    0.49
    情緒
    0.49
     अगर
    0.49
     because
    0.48
    Activations Density 0.000%

    No Known Activations