© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30900
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ):=
    0.42
    kungan
    0.40
    zuge
    0.38
     lbl
    0.37
     teniendo
    0.36
     devenue
    0.36
    gian
    0.36
     conflictos
    0.35
     tecnológicas
    0.35
    setVisibility
    0.35
    POSITIVE LOGITS
     निजी
    0.37
    爱
    0.36
    Ç
    0.34
    หยุด
    0.33
    อย
    0.33
    国王
    0.33
     oeuvre
    0.33
     ასევე
    0.32
     circles
    0.32
    แก้
    0.32
    Activations Density 0.002%

    No Known Activations