© 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. 95804
    Prev
    Next
    INDEX
    Explanations

    compacted material, best rehab

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

    critical, reliable, statements

    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
     isDisabled
    0.48
    Thats
    0.44
    UpSync
    0.44
    Ahh
    0.43
    如果要
    0.43
    鐒
    0.43
    버
    0.43
    施
    0.42
    瑷
    0.42
    办公
    0.42
    POSITIVE LOGITS
    stellar
    0.53
    stel
    0.51
    ,
    0.49
    reliable
    0.49
    charged
    0.47
    :
    0.47
    reli
    0.46
    rets
    0.46
    seed
    0.46
    នៅក្នុង
    0.46
    Activations Density 0.002%

    No Known Activations