© 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. 220251
    Prev
    Next
    INDEX
    Explanations

    grateful, cause, slave

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

    future predictions and potential integration

    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
    i
    0.55
     karakteristik
    0.52
     vostre
    0.50
    פור
    0.48
     tarihi
    0.48
    🤑
    0.48
    gina
    0.47
    }$.
    0.47
     KPMG
    0.46
     CLIENTI
    0.46
    POSITIVE LOGITS
     steeper
    0.45
     suffers
    0.44
    を通
    0.44
     calmer
    0.44
    0.43
     Baat
    0.43
     wing
    0.43
    궂
    0.42
    を経
    0.42
     electrolyte
    0.41
    Activations Density 0.001%

    No Known Activations