© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161471
    Prev
    Next
    INDEX
    Explanations

    party, few, confident, reserved, later, inspirational, Centre

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

    assuredness, past connections, intellectual focus

    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
    وري
    0.51
     .
    0.49
     rú
    0.49
     éste
    0.48
    鏈
    0.47
     do
    0.47
     ésta
    0.47
     inv
    0.46
     في
    0.46
     limite
    0.46
    POSITIVE LOGITS
    স্থানীয়
    0.41
     instigated
    0.41
    ್ಣ
    0.41
    ্ধু
    0.41
    身份证
    0.40
     सहाय
    0.40
    ClientId
    0.40
    炖
    0.39
    锣
    0.39
    टीन
    0.39
    Activations Density 0.000%

    No Known Activations