© 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. 251909
    Prev
    Next
    INDEX
    Explanations

    conversions with input

    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
    atang
    0.57
    StoredKeys
    0.50
    ScriptBuf
    0.50
    ສໍາ
    0.50
    ্
    0.48
    ດ
    0.48
     বৃষ্টির
    0.48
    '/>
    0.47
    伖
    0.46
     ପ୍ର
    0.46
    POSITIVE LOGITS
     mene
    0.51
    ę
    0.47
    nál
    0.47
     type
    0.46
     https
    0.45
     parecía
    0.45
     maja
    0.44
    0.44
     Quer
    0.43
     limits
    0.43
    Activations Density 0.001%

    No Known Activations