© 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. 158165
    Prev
    Next
    INDEX
    Explanations

    Pentacles, cash flow, physical descriptions

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

    regex negated character sets

    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
    麝
    0.48
     হাইক
    0.47
    дук
    0.46
    ственные
    0.45
    TakePicture
    0.45
    ֲ
    0.45
    Star
    0.45
    个人
    0.45
    附
    0.43
    谭
    0.43
    POSITIVE LOGITS
     achievement
    0.57
     protection
    0.56
     opportunity
    0.55
     evasion
    0.53
     acquittal
    0.53
    ynth
    0.52
     manifesto
    0.52
     Iberian
    0.52
     objectives
    0.51
     orbit
    0.51
    Activations Density 0.000%

    No Known Activations