© 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. 165539
    Prev
    Next
    INDEX
    Explanations

    financial investment consulting

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

    overgrown patches, questionable karaoke, strains

    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
    oul
    0.54
    adas
    0.53
    ô
    0.52
    ole
    0.50
     institute
    0.49
     microtubules
    0.48
     vä
    0.48
    ᡠ
    0.47
    ürm
    0.47
     जनसंख्या
    0.47
    POSITIVE LOGITS
    Thr
    0.52
    IGO
    0.47
    rawing
    0.45
     Galloway
    0.45
    логи
    0.44
    אס
    0.44
    煒
    0.44
    Irish
    0.44
     salads
    0.43
     כדי
    0.43
    Activations Density 0.000%

    No Known Activations