© 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. 2290
    Prev
    Next
    INDEX
    Explanations

    image size, dimensions, or `figsize`

    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
    feather
    0.39
     Eleventh
    0.38
    <unused51>
    0.36
    फेस
    0.35
    ).”
    0.35
    }^{+}+
    0.35
    urahan
    0.33
    __."
    0.33
    requestFocus
    0.33
    deoxy
    0.33
    POSITIVE LOGITS
    稳定性
    0.36
    admin
    0.36
    στα
    0.35
     Admin
    0.35
     admin
    0.35
    cou
    0.34
     Administ
    0.33
    figsize
    0.33
     расскажем
    0.33
    ∣
    0.33
    Activations Density 0.002%

    No Known Activations