© 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. 27124
    Prev
    Next
    INDEX
    Explanations

    quantity or number

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

    expected reward calculation

    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
    睜
    0.48
    紧急
    0.48
    Depos
    0.42
     緊急
    0.42
    🔁
    0.42
    స్తే
    0.42
    bestos
    0.41
    😟
    0.41
    做
    0.41
     MAKING
    0.41
    POSITIVE LOGITS
     Diaz
    0.49
    good
    0.48
     kode
    0.47
     tempered
    0.47
     DIA
    0.46
     Jimenez
    0.46
    ﺂ
    0.46
     color
    0.46
     dia
    0.46
     Dia
    0.46
    Activations Density 0.000%

    No Known Activations