© 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. 175662
    Prev
    Next
    INDEX
    Explanations

    foreign words and definitions

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

    descriptive list items preceded by asterisks

    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
    padă
    0.47
    eda
    0.46
    𝓪
    0.44
     a
    0.43
     amplifier
    0.43
     an
    0.42
     taka
    0.42
     rollerskates
    0.42
     seaside
    0.42
     sms
    0.41
    POSITIVE LOGITS
    тивних
    0.46
    ベクトル
    0.45
    㓞
    0.45
     inexplic
    0.44
     സമ്മ
    0.44
    不正
    0.44
    圧力
    0.44
     Meinung
    0.43
     disequ
    0.43
     Druck
    0.42
    Activations Density 0.000%

    No Known Activations