© 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. 109065
    Prev
    Next
    INDEX
    Explanations

    spatial relations

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

    experienced sexual trauma

    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
     Dentist
    0.46
    就连
    0.46
     ജോലി
    0.45
     effekt
    0.45
    <unused5>
    0.42
     býval
    0.41
     banished
    0.41
     effectual
    0.41
     backstory
    0.41
     Apocalypse
    0.41
    POSITIVE LOGITS
    あるいは
    0.46
    rightarrow
    0.46
     シ
    0.44
     подве
    0.43
    sas
    0.43
     anomalies
    0.42
     ヘア
    0.42
     marzo
    0.41
    phantom
    0.41
    malign
    0.41
    Activations Density 0.000%

    No Known Activations