© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181866
    Prev
    Next
    INDEX
    Explanations

    instructions or common follow-ups

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

    requesting further information

    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
     agrees
    0.55
     first
    0.51
     webinar
    0.48
     rejects
    0.48
     says
    0.47
     adhesion
    0.47
     €.
    0.47
     differs
    0.46
     liné
    0.46
     reduces
    0.46
    POSITIVE LOGITS
    us
    0.59
    к
    0.59
     بودند
    0.52
     были
    0.51
    Leod
    0.51
    კ
    0.51
    slaught
    0.50
    кторов
    0.50
    getDrawable
    0.50
    конец
    0.49
    Activations Density 0.010%

    No Known Activations