© 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. 96529
    Prev
    Next
    INDEX
    Explanations

    inlay technique, produce all

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

    controlling relationships, percentages, affect LLM

    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
     Graham
    0.47
    ^{-
    0.47
     Ked
    0.46
     unwell
    0.46
     intrad
    0.46
     Ameri
    0.46
     apprehended
    0.45
    abend
    0.44
    um
    0.44
     Weber
    0.44
    POSITIVE LOGITS
     ಬು
    0.56
    }$&$-
    0.46
     두
    0.46
     турында
    0.45
    抟
    0.45
    poons
    0.43
     লজ্জ
    0.42
    ಾಲ
    0.41
     ನಾಲ್
    0.41
    赚
    0.41
    Activations Density 0.000%

    No Known Activations