© 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. 35436
    Prev
    Next
    INDEX
    Explanations

    have just / starting to / are available

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

    classical job queues

    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
    🧹
    0.43
    ,
    0.43
     consistent
    0.43
    ogeneity
    0.42
    lever
    0.42
     measuring
    0.41
    世話
    0.41
    狗
    0.41
    sm
    0.41
    нке
    0.40
    POSITIVE LOGITS
     မိ
    0.55
     衣
    0.54
     ध्वनि
    0.54
    ት
    0.51
    ']['
    0.51
     枚
    0.51
     halfCanvas
    0.50
     цієї
    0.50
     этой
    0.49
     BuildableName
    0.49
    Activations Density 0.000%

    No Known Activations