© 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. 20869
    Prev
    Next
    INDEX
    Explanations

    rubberized laptop cases

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

    library usage or technical implementation

    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
    ებლ
    0.49
    త్ప
    0.49
    ៤
    0.48
    followlike
    0.47
    𝟮
    0.47
    bitkan
    0.47
    𝟰
    0.47
    собенности
    0.46
    leukin
    0.46
    羋
    0.46
    POSITIVE LOGITS
    0.53
     or
    0.52
     Fan
    0.52
     或者
    0.50
     and
    0.49
     Hug
    0.48
     Park
    0.47
     oder
    0.47
     Teacher
    0.46
     Group
    0.46
    Activations Density 0.000%

    No Known Activations