© 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. 69644
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign characters

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

    bad descriptions

    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
     Morocco
    0.45
     препарата
    0.45
     אטאטורק
    0.44
    자와
    0.43
    踞
    0.43
     Pandora
    0.42
     ஆர்வ
    0.42
    隼
    0.41
    默默
    0.41
     करवाए
    0.41
    POSITIVE LOGITS
    ፡
    0.50
    ،
    0.47
     revisited
    0.47
     hindsight
    0.46
     erstmals
    0.44
    inker
    0.43
     rück
    0.43
    inib
    0.41
    шон
    0.41
    نین
    0.40
    Activations Density 0.005%

    No Known Activations