© 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. 137318
    Prev
    Next
    INDEX
    Explanations

    clarifying definitions or examples

    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
    ˵
    0.39
    
    0.39
    jord
    0.38
    ",
    0.37
    িয়াছিল
    0.37
     assume
    0.36
    ्ड
    0.36
     assumed
    0.36
     spine
    0.36
    »,
    0.36
    POSITIVE LOGITS
    㻐
    0.44
     Without
    0.44
     DTS
    0.40
     மூன்ற
    0.39
     함께
    0.39
    ړو
    0.38
    ሹ
    0.38
    Without
    0.37
     MOM
    0.37
     LTS
    0.37
    Activations Density 0.000%

    No Known Activations