© 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. 252106
    Prev
    Next
    INDEX
    Explanations

    find out what's worth doing

    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
     dip
    0.47
     catapult
    0.45
    MDEwOlJlcG
    0.45
    ।
    0.44
     certific
    0.43
     canaux
    0.43
     entreprises
    0.43
     seule
    0.43
     priv
    0.42
     pilotes
    0.42
    POSITIVE LOGITS
    的服务
    0.50
    嫒
    0.49
    尔多
    0.49
    蔗
    0.48
    }=(\
    0.45
    BUR
    0.45
    艰
    0.45
    的不
    0.44
    SAL
    0.44
    檎
    0.44
    Activations Density 0.000%

    No Known Activations