© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63762
    Prev
    Next
    INDEX
    Explanations

    del Toro, trained, done

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

    scripts and code

    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
    Key
    0.55
    ה
    0.53
    ax
    0.49
    Avoid
    0.49
     كذلك
    0.48
    アウトドア
    0.48
    琀
    0.48
    ية
    0.48
    決して
    0.48
    வோ
    0.47
    POSITIVE LOGITS
     penthouse
    0.50
     pyrolysis
    0.47
     ferritin
    0.46
     preacher
    0.46
     alchemy
    0.46
     supernova
    0.45
     vetted
    0.45
     melanoma
    0.44
     laz
    0.44
     ferrite
    0.44
    Activations Density 0.000%

    No Known Activations