© 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. 104570
    Prev
    Next
    INDEX
    Explanations

    instances, including forwards, jumping, when

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

    about aesthetics

    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
     কলেজের
    0.50
    蘚
    0.47
     presente
    0.46
     Season
    0.45
     Wire
    0.45
     Ven
    0.45
     Due
    0.44
     φ
    0.43
     mnoho
    0.43
     Bài
    0.43
    POSITIVE LOGITS
    ;
    0.50
    콰
    0.46
    재
    0.44
    Cascade
    0.43
    ബൈ
    0.43
    MDET
    0.43
    };
    0.42
    FIT
    0.42
    촤
    0.42
    Costs
    0.41
    Activations Density 0.000%

    No Known Activations