© 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. 247604
    Prev
    Next
    INDEX
    Explanations

    non-English and English words

    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
    aset
    0.48
    aS
    0.47
     comenzó
    0.44
     begun
    0.44
    [...]
    0.43
     III
    0.42
    abad
    0.41
                     
    0.40
     TestBed
    0.40
     VII
    0.40
    POSITIVE LOGITS
     bloke
    0.50
    ゲーム
    0.45
    そういう
    0.45
    ですね
    0.44
    That
    0.42
    じゃない
    0.41
    තුරු
    0.41
     बटन
    0.41
     shoving
    0.40
    呔
    0.40
    Activations Density 0.244%

    No Known Activations