© 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. 203800
    Prev
    Next
    INDEX
    Explanations

    business and operations

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

    bullet points and colons

    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
    le
    0.56
    ('/').
    0.53
    lel
    0.52
    ixin
    0.49
    רים
    0.48
    ንም
    0.48
    ijl
    0.47
    -'+
    0.46
    iala
    0.46
     अहं
    0.46
    POSITIVE LOGITS
     Guzman
    0.47
     Certainly
    0.46
     doubl
    0.45
    puma
    0.44
     unsupported
    0.43
     pockets
    0.42
    আপনি
    0.42
    狛
    0.42
    ̹
    0.41
    Both
    0.41
    Activations Density 0.000%

    No Known Activations