© 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. 50913
    Prev
    Next
    INDEX
    Explanations

    fast actors

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

    escalate tensions or start repeat

    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
    ều
    0.46
     grasa
    0.46
    βα
    0.45
    ະພັນ
    0.43
     a
    0.42
     તર
    0.41
    DataBase
    0.41
    Bearer
    0.40
     Хоро
    0.40
     flowing
    0.40
    POSITIVE LOGITS
     배우
    0.46
     actresses
    0.46
     pilgr
    0.43
    к
    0.41
     인간
    0.40
     Actress
    0.39
     actors
    0.39
     Politique
    0.39
    ]
    0.39
     vuos
    0.38
    Activations Density 0.000%

    No Known Activations