© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16095
    Prev
    Next
    INDEX
    Explanations

    organizations and government bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zanim
    -0.99
    氏が
    -0.98
    氏は
    -0.96
    兒童
    -0.91
     from
    -0.86
     предполага
    -0.86
    заи
    -0.84
    ঝ
    -0.82
     no
    -0.82
    댄
    -0.81
    POSITIVE LOGITS
     already
    1.03
     WaitForSeconds
    0.98
     Pristupljeno
    0.93
    怠
    0.93
    WINNER
    0.92
     acos
    0.89
    ritage
    0.88
    ذهب
    0.88
     continuer
    0.85
     dizer
    0.85
    Activations Density 0.029%

    No Known Activations