© 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. 144103
    Prev
    Next
    INDEX
    Explanations

    assassination bullet kills

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

    likely motivations or claims

    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
    ūt
    0.51
    ua
    0.48
     jumlah
    0.45
    _
    0.45
    ina
    0.44
     pernah
    0.44
    ropic
    0.43
    perm
    0.43
    olina
    0.43
    āra
    0.43
    POSITIVE LOGITS
     cocktails
    0.50
     exécut
    0.45
     legends
    0.45
     observaciones
    0.44
     regrett
    0.43
     speeches
    0.43
    鎧
    0.43
     protagonists
    0.43
    観察
    0.43
     revolver
    0.42
    Activations Density 0.001%

    No Known Activations