© 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. 241966
    Prev
    Next
    INDEX
    Explanations

    gay, expanding, tools, not, aim

    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
    Aircraft
    0.51
    ់
    0.51
    ន្ទ
    0.49
    يط
    0.48
     showc
    0.46
    polyline
    0.44
     squadra
    0.43
     mane
    0.43
    h
    0.43
     jaane
    0.43
    POSITIVE LOGITS
    温
    0.47
     तेज
    0.46
    oure
    0.46
    募集
    0.46
     apparten
    0.45
     राजस्थान
    0.45
     会
    0.45
    anned
    0.44
     agre
    0.44
    传递
    0.44
    Activations Density 0.000%

    No Known Activations