© 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. 99426
    Prev
    Next
    INDEX
    Explanations

    listing items / pictures

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

    i'm not saying... but

    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
    Protein
    0.43
    Technical
    0.43
    條
    0.43
    Malcolm
    0.43
     szint
    0.42
    ওয়া
    0.41
     Site
    0.40
     wag
    0.40
    ورش
    0.40
    游
    0.40
    POSITIVE LOGITS
    idamente
    0.52
    çado
    0.52
     sleeveless
    0.50
    blusas
    0.50
    ्रिया
    0.49
    blusa
    0.49
    ap
    0.47
    ‼️
    0.47
     aides
    0.47
    chließlich
    0.46
    Activations Density 0.001%

    No Known Activations