© 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. 33510
    Prev
    Next
    INDEX
    Explanations

    one block

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

    beyond basic functionality

    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
    競技
    0.44
     schwe
    0.43
    績
    0.42
     sk
    0.40
     দলীয়
    0.39
     對
    0.39
    賑
    0.39
    國
    0.38
    suit
    0.37
    所有人
    0.37
    POSITIVE LOGITS
    ندی
    0.54
     incontr
    0.48
     flashbacks
    0.47
    Stored
    0.47
     منجر
    0.46
     случаях
    0.45
     delusions
    0.44
    存储
    0.44
     alarming
    0.44
    ഥ
    0.44
    Activations Density 0.000%

    No Known Activations