© 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. 41607
    Prev
    Next
    INDEX
    Explanations

    locations and products

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

    sales, memberships, properties

    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
     bathrooms
    0.46
    詠
    0.45
     リュ
    0.43
     ölüm
    0.43
     consapevole
    0.42
    心的
    0.42
     réellement
    0.41
     görsel
    0.41
    饴
    0.41
    ↵
    0.40
    POSITIVE LOGITS
     expressway
    0.47
    BAND
    0.47
    ವಾ
    0.47
    র্ত
    0.45
    वा
    0.45
    BASE
    0.44
    band
    0.44
    }}{\
    0.44
    Base
    0.43
    PROM
    0.43
    Activations Density 0.000%

    No Known Activations