© 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. 96784
    Prev
    Next
    INDEX
    Explanations

    Sunday Morning we have

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

    versatility and talent

    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
    或
    0.49
     или
    0.46
     oder
    0.46
    而不
    0.45
     hoặc
    0.45
    id
    0.44
    性和
    0.44
    㝡
    0.44
    や
    0.43
    query
    0.43
    POSITIVE LOGITS
    ാരം
    0.49
     versatility
    0.49
     दमदार
    0.47
     talented
    0.45
     wholeheartedly
    0.45
    त्व
    0.44
    継続
    0.44
    Peer
    0.44
     상승
    0.43
     discurso
    0.43
    Activations Density 0.001%

    No Known Activations