© 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. 36825
    Prev
    Next
    INDEX
    Explanations

    profile and registration descriptions

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

    online

    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
     ات
    0.48
    渔
    0.46
     కూడా
    0.46
    reszt
    0.46
    柅
    0.44
    发动
    0.44
    禳
    0.44
    剜
    0.43
    െന്നും
    0.43
    泬
    0.43
    POSITIVE LOGITS
    STD
    0.37
     equivalents
    0.37
     UPPER
    0.37
     Recognized
    0.36
    名稱
    0.36
     Chengdu
    0.36
     Equivalent
    0.35
    <0x0D>
    0.35
     recognized
    0.35
     pch
    0.35
    Activations Density 0.010%

    No Known Activations