© 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. 97405
    Prev
    Next
    INDEX
    Explanations

    junk and embedded notes

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

    mathematical negation (¬)

    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
    и
    0.52
    wärm
    0.50
    in
    0.49
    on
    0.45
     তবু
    0.45
    მოს
    0.42
    ла
    0.42
     modernity
    0.42
    萦
    0.42
    сть
    0.41
    POSITIVE LOGITS
    fficial
    0.54
    tmpobj
    0.54
    ᵐ
    0.54
    ക്ടര്‍
    0.50
    bmp
    0.49
    </s>
    0.49
     အရ
    0.49
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.48
    gm
    0.48
     എല്ലാവ
    0.48
    Activations Density 0.000%

    No Known Activations