© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211509
    Prev
    Next
    INDEX
    Explanations

    end of sentence

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

    imminent, Changing, worthy, manipulate, cm, layer

    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
    carte
    0.54
     الإص
    0.50
    kör
    0.49
    texte
    0.48
    3
    0.48
    akti
    0.48
    cds
    0.47
    glb
    0.46
    pras
    0.46
    zt
    0.46
    POSITIVE LOGITS
    樯
    0.46
     ARTS
    0.45
     Non
    0.44
     istnieje
    0.44
    না
    0.42
     ONT
    0.42
     Zeitraum
    0.42
     Amts
    0.42
     its
    0.42
     MID
    0.42
    Activations Density 0.000%

    No Known Activations