© 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. 136392
    Prev
    Next
    INDEX
    Explanations

    moments and time units

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

    moment and momentum

    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
    蠢
    0.47
    馅
    0.46
    职责
    0.45
    umbnail
    0.45
    设备的
    0.45
    衬
    0.45
    敌
    0.44
    पालिका
    0.44
    那种
    0.44
    ͇
    0.44
    POSITIVE LOGITS
     spent
    0.73
    spent
    0.63
     spends
    0.59
     Spent
    0.58
     spend
    0.56
    Spent
    0.56
     elapsed
    0.48
     Instant
    0.48
    elapsed
    0.48
    instant
    0.45
    Activations Density 0.026%

    No Known Activations