© 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. 102005
    Prev
    Next
    INDEX
    Explanations

    crafted, designed, tuned

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

    created or affordable items

    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
    ጾ
    0.50
     הט
    0.47
    은
    0.47
    జ
    0.47
    יה
    0.46
    จ
    0.46
    출
    0.46
    ኔ
    0.46
    有助于
    0.46
    _$
    0.44
    POSITIVE LOGITS
    den
    0.55
    personalised
    0.52
    crafted
    0.51
    tuned
    0.51
     crafted
    0.49
    coating
    0.48
    hasta
    0.47
    ported
    0.47
    designated
    0.47
    designed
    0.47
    Activations Density 0.002%

    No Known Activations