© 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. 28772
    Prev
    Next
    INDEX
    Explanations

    made: origin, composition, purpose

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

    made up of

    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
    0
    0.57
    ৬০
    0.54
    5
    0.52
    KNOWN
    0.52
    LAH
    0.50
    GREEN
    0.50
    6
    0.50
     экскур
    0.50
    9
    0.50
    ENAME
    0.49
    POSITIVE LOGITS
     geschaffen
    0.66
    ات
    0.56
     feita
    0.53
    ccion
    0.52
     AGS
    0.52
     gemacht
    0.51
    របស់
    0.50
     dibuat
    0.50
    يت
    0.49
    gens
    0.49
    Activations Density 0.042%

    No Known Activations