© 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. 37601
    Prev
    Next
    INDEX
    Explanations

    the one I

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

    ligament and nerve anatomy

    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
    陷
    0.43
     armature
    0.40
    Carroll
    0.40
    セラ
    0.40
    下が
    0.40
    습
    0.39
    덥
    0.39
     emerges
    0.39
     contrived
    0.39
    ﾄ
    0.39
    POSITIVE LOGITS
    flix
    0.46
     slike
    0.43
    र्ण
    0.43
    weaver
    0.41
     glas
    0.41
     Nantes
    0.41
     rivalry
    0.41
     legado
    0.41
     glowing
    0.40
     dazzling
    0.40
    Activations Density 0.005%

    No Known Activations