© 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. 62771
    Prev
    Next
    INDEX
    Explanations

    action and achievement phrases

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

    hit + common words

    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
    us
    0.62
    ু
    0.56
    りん
    0.55
    filament
    0.55
    hepatic
    0.53
    ä
    0.53
    り
    0.52
     hadrons
    0.52
    WARD
    0.51
    FAR
    0.51
    POSITIVE LOGITS
     hit
    1.02
     hits
    0.84
    hit
    0.77
     HIT
    0.76
     hitting
    0.75
     Hit
    0.73
     Hits
    0.72
     हिट
    0.70
    1
    0.70
    hits
    0.70
    Activations Density 0.027%

    No Known Activations