© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168410
    Prev
    Next
    INDEX
    Explanations

    allow to track

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

    relentlessly hunting, treatment sessions, key clicked

    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
    :
    0.50
     john
    0.46
     hat
    0.45
     reverse
    0.45
     T
    0.45
     Cooperative
    0.45
     Bang
    0.45
    ।
    0.45
    -
    0.44
     Connect
    0.44
    POSITIVE LOGITS
    cèle
    0.54
    ционе
    0.51
    Afghan
    0.50
    フィス
    0.49
    aunque
    0.48
    物語
    0.47
    statusBar
    0.47
    unfortunately
    0.47
    ‌ی
    0.47
    మార్
    0.47
    Activations Density 0.001%

    No Known Activations