© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2196
    Prev
    Next
    INDEX
    Explanations

    RAINN National Sexual Assault Hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Minimal
    0.23
    Confirmation
    0.23
    Deletion
    0.23
     Recherches
    0.21
    砶
    0.21
    Always
    0.21
    Whole
    0.21
    Percent
    0.21
    
    0.21
    Remain
    0.21
    POSITIVE LOGITS
     l
    0.21
    u
    0.21
    holm
    0.20
     nazionale
    0.20
     pravil
    0.19
    <unused1145>
    0.19
     t
    0.19
     eski
    0.19
    ba
    0.19
    vide
    0.19
    Activations Density 0.084%

    No Known Activations