© 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. 24754
    Prev
    Next
    INDEX
    Explanations

    related diseases

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

    decomposition, satisfies, concentrate, timers, hash

    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
    的
    0.45
    後
    0.44
    ANG
    0.41
    سي
    0.41
    og
    0.39
    的标准
    0.39
     knob
    0.39
     王
    0.38
     च
    0.38
     grafted
    0.38
    POSITIVE LOGITS
    rivit
    0.52
     THEM
    0.50
    them
    0.46
     OVER
    0.46
     Филип
    0.45
    lerden
    0.44
    lerimiz
    0.44
     вопроса
    0.43
    㧋
    0.42
     Medik
    0.41
    Activations Density 0.000%

    No Known Activations