© 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. 6297
    Prev
    Next
    INDEX
    Explanations

    preferred or plus qualifications

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

    word in contrast to token

    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
     ಪರಿಸ
    0.42
    比如说
    0.41
    AGING
    0.38
    比如說
    0.38
    Basically
    0.37
     είναι
    0.37
    大好き
    0.37
    药品
    0.37
    aging
    0.37
    ໃຊ້
    0.36
    POSITIVE LOGITS
     but
    0.60
     nhưng
    0.56
     लेकिन
    0.55
     কিন্তু
    0.55
     لكن
    0.54
     αλλά
    0.54
     ngunit
    0.54
     ancak
    0.53
     אך
    0.52
     પરંતુ
    0.51
    Activations Density 0.001%

    No Known Activations