© 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. 24169
    Prev
    Next
    INDEX
    Explanations

    numbers followed by comma

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

    emotional release

    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
     હજાર
    0.53
    すべて
    0.49
    持ち
    0.48
    тике
    0.48
    󠁿
    0.47
    दारों
    0.47
    кість
    0.47
    тей
    0.47
    <0x19>
    0.47
    プロジェクト
    0.46
    POSITIVE LOGITS
     nanow
    0.46
     ingestion
    0.45
     Rm
    0.45
     Bibliothek
    0.44
    因为它
    0.44
     fragment
    0.43
     (((
    0.43
     kaca
    0.43
     han
    0.43
     ic
    0.43
    Activations Density 0.000%

    No Known Activations