© 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. 224796
    Prev
    Next
    INDEX
    Explanations

    areas, it, you, size

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

    feature interactions and sounds

    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
    ł
    0.50
     battered
    0.46
     disastrous
    0.45
     peligros
    0.44
    後は
    0.43
     debacle
    0.42
    ól
    0.42
    ological
    0.41
    ONE
    0.41
     duelo
    0.41
    POSITIVE LOGITS
     molecules
    0.51
    ármaz
    0.51
    ाइंड
    0.50
    মনির
    0.50
    Компания
    0.50
    Š
    0.50
    HeaderAccept
    0.49
     strtok
    0.49
    atoms
    0.48
     estradiol
    0.48
    Activations Density 0.000%

    No Known Activations