© 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. 180714
    Prev
    Next
    INDEX
    Explanations

    describing requirements and features

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

    active, restart, requires

    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
    itudine
    0.53
     wagons
    0.53
     straps
    0.47
     bruised
    0.46
     strap
    0.46
    ፔ
    0.45
     promote
    0.45
     allergies
    0.45
     rubble
    0.45
     lobbies
    0.44
    POSITIVE LOGITS
     Той
    0.44
     AVEN
    0.44
    rjust
    0.42
     Intelli
    0.41
    Ｊ
    0.41
     పర
    0.41
     ditambah
    0.41
    وارد
    0.41
    HAV
    0.41
    ები
    0.40
    Activations Density 0.000%

    No Known Activations