© 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. 193770
    Prev
    Next
    INDEX
    Explanations

    to store

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

    specific explanations or topics

    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
    設定
    0.46
    _{\
    0.43
    encies
    0.42
     Kaplan
    0.42
    拃
    0.42
    jetbrains
    0.42
    矽
    0.41
    urt
    0.41
    疆
    0.41
    ur
    0.41
    POSITIVE LOGITS
     reimbursed
    0.54
     /^
    0.54
     reimburse
    0.51
    la
    0.49
    מר
    0.49
     copi
    0.48
     rejoined
    0.47
    seudo
    0.47
     bist
    0.47
     improper
    0.46
    Activations Density 0.001%

    No Known Activations