© 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. 186363
    Prev
    Next
    INDEX
    Explanations

    sharing heart

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

    SMS Focused, Minutes, recipes

    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
    瀉
    0.53
    蛋白质
    0.51
    ナス
    0.50
    ёма
    0.50
    阶
    0.46
    鲈
    0.46
    কতা
    0.46
     Шта
    0.46
     能力
    0.46
    ፑ
    0.46
    POSITIVE LOGITS
     pren
    0.52
     familiale
    0.50
     Heart
    0.50
     Feliz
    0.50
     heart
    0.50
     hechos
    0.50
    lease
    0.48
    heart
    0.48
    port
    0.47
    :
    0.47
    Activations Density 0.000%

    No Known Activations