© 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. 97
    Prev
    Next
    INDEX
    Explanations

    with oven or hob

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

    describing time, state, or possession

    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
    Хо
    0.49
    갸
    0.46
     inducible
    0.45
     defamation
    0.44
    送料
    0.44
     significantly
    0.43
     addiction
    0.42
    </strong>
    0.41
     deficiency
    0.41
    店頭
    0.41
    POSITIVE LOGITS
    nellement
    0.50
     chức
    0.49
    jande
    0.47
    keszt
    0.46
    嘗
    0.46
    estellt
    0.46
    thisTrack
    0.46
    mss
    0.46
    fonction
    0.45
    geht
    0.45
    Activations Density 0.000%

    No Known Activations