© 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. 164469
    Prev
    Next
    INDEX
    Explanations

    inter or instead

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

    exploring possibilities

    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
     neglig
    0.40
    iros
    0.40
    RECEIVED
    0.39
    இ
    0.39
     Concerned
    0.39
     Hinter
    0.38
     करिए
    0.38
    b
    0.38
     Coaches
    0.38
     Definitely
    0.38
    POSITIVE LOGITS
    测
    0.52
    ulum
    0.46
    véd
    0.46
     лаборатор
    0.46
    视角
    0.45
    ontan
    0.44
     неболь
    0.44
     иллю
    0.44
    acier
    0.43
     остав
    0.42
    Activations Density 0.000%

    No Known Activations