© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134755
    Prev
    Next
    INDEX
    Explanations

    learning and adaptation

    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
    othèque
    0.43
    hões
    0.41
    пра
    0.40
    brellas
    0.39
    .•
    0.39
    ೂರ್ಣ
    0.38
    ⸱
    0.38
    umsal
    0.37
    fnamefont
    0.37
    ">*
    0.37
    POSITIVE LOGITS
    $/,
    0.38
     learner
    0.37
     (/
    0.36
     img
    0.36
     hostage
    0.36
     logarith
    0.35
     porte
    0.35
     heart
    0.35
     charting
    0.35
     anuv
    0.35
    Activations Density 0.005%

    No Known Activations