© 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. 105125
    Prev
    Next
    INDEX
    Explanations

    identifying "Label:" or "Labels:"

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

    html label for

    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
     i
    0.49
    精灵
    0.49
    lung
    0.47
    lip
    0.45
     ecz
    0.45
    lodge
    0.45
    like
    0.44
     embers
    0.44
     kang
    0.43
    tak
    0.43
    POSITIVE LOGITS
    𝕕
    0.51
    逺
    0.50
    चार
    0.48
    フト
    0.47
     revêt
    0.46
    Croatian
    0.46
     für
    0.45
    ссмотрим
    0.45
    Télé
    0.45
    ﺪ
    0.44
    Activations Density 0.000%

    No Known Activations