© 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. 95074
    Prev
    Next
    INDEX
    Explanations

    legal and specific entities

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

    cognitive impairment, poor decision-making, compulsive behavior

    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
    Upload
    0.42
    Toolbar
    0.42
    FFFF
    0.42
    Flat
    0.41
    Fcn
    0.41
    ➟
    0.40
    SpriteCollision
    0.40
    /*
    0.39
    నో
    0.39
    ([...
    0.39
    POSITIVE LOGITS
     servi
    0.48
     proche
    0.48
    ग्राह
    0.47
     نمائ
    0.46
     souten
    0.45
     olisi
    0.44
     rhetorical
    0.43
     kath
    0.43
    ‖</
    0.43
     calorimetric
    0.43
    Activations Density 0.000%

    No Known Activations