© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29941
    Prev
    Next
    INDEX
    Explanations

    drilling and shaping material

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

    Repeat, shadowing, sequential actions, questionnaires

    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
    gó
    0.49
    ِ
    0.46
    โน
    0.45
    驱
    0.45
     transplantation
    0.43
     mismas
    0.43
    ズム
    0.43
    ("../../
    0.43
    несе
    0.42
    ṕ
    0.42
    POSITIVE LOGITS
     Brake
    0.47
     Drill
    0.47
     showing
    0.46
     Ingl
    0.46
     drilled
    0.46
     Drilling
    0.45
     Alloy
    0.45
    O
    0.44
     illustrating
    0.44
     drilling
    0.43
    Activations Density 0.000%

    No Known Activations