© 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. 217053
    Prev
    Next
    INDEX
    Explanations

    the choice of

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

    murder

    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
     carre
    0.43
    ាំង
    0.43
     ক্যার
    0.43
    pleClass
    0.43
     Букмекер
    0.42
    áže
    0.42
    öffnet
    0.41
    谲
    0.41
    etään
    0.40
    <unused3>
    0.40
    POSITIVE LOGITS
    Me
    0.57
    ’
    0.57
    ema
    0.52
    GIN
    0.50
    ،
    0.50
     I
    0.50
    ika
    0.50
    aut
    0.50
     T
    0.49
    ivo
    0.49
    Activations Density 0.001%

    No Known Activations