© 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. 22535
    Prev
    Next
    INDEX
    Explanations

    seeking specific items

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

    no scientifically verified evidence

    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
     explotación
    0.57
    களை
    0.55
    ك
    0.55
    japan
    0.55
    ート
    0.52
    प्रा
    0.51
    ncol
    0.51
    нициа
    0.51
    らし
    0.51
     एकदा
    0.51
    POSITIVE LOGITS
     came
    0.44
     steeped
    0.44
     murdered
    0.42
     grew
    0.40
    <0xD0>
    0.38
     structured
    0.38
     Responses
    0.38
     embroiled
    0.38
     harmed
    0.38
     cambió
    0.38
    Activations Density 0.000%

    No Known Activations