© 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. 100421
    Prev
    Next
    INDEX
    Explanations

    acknowledgment receipt

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

    Black communities and families

    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
     bakter
    0.46
    arnings
    0.45
     linings
    0.45
     这
    0.44
     Islam
    0.44
     aspetto
    0.43
     elastic
    0.42
    Skippable
    0.42
     отверсти
    0.42
    arns
    0.42
    POSITIVE LOGITS
     acknowledgment
    0.46
    ･
    0.44
    ம்
    0.44
    ྔ
    0.43
    紗
    0.42
    翁
    0.41
    ே
    0.41
     Lorentzian
    0.40
    榎
    0.40
    ቻ
    0.40
    Activations Density 0.001%

    No Known Activations