© 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. 178790
    Prev
    Next
    INDEX
    Explanations

    range, herds, hospital, website

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

    `str` `fever` `gear`

    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
    ᱴ
    0.49
    ℝ
    0.44
    Ug
    0.44
    ޒ
    0.43
    Stocks
    0.43
    Carter
    0.42
     encuentran
    0.42
    ᆹ
    0.42
    LJ
    0.41
    Rim
    0.41
    POSITIVE LOGITS
    ্বার
    0.55
     quantized
    0.49
    overlaps
    0.47
    挚
    0.45
    ност
    0.44
     qubit
    0.43
     kwargs
    0.43
     Ornament
    0.43
    দানের
    0.43
     setattr
    0.43
    Activations Density 0.000%

    No Known Activations