© 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. 208288
    Prev
    Next
    INDEX
    Explanations

    .gr / IRB / regardless

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

    logical connectors and specific technical terms

    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
    зів
    0.52
    ści
    0.45
    íticos
    0.45
    jež
    0.45
    ኻ
    0.45
    Vale
    0.44
    kh
    0.44
    wer
    0.43
    ográficas
    0.43
     motives
    0.43
    POSITIVE LOGITS
    .。
    0.52
    時間は
    0.49
     जानने
    0.48
     doa
    0.46
    忘
    0.46
     ground
    0.45
    にか
    0.45
     trao
    0.44
     Regno
    0.44
    時間が
    0.43
    Activations Density 0.000%

    No Known Activations