© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98483
    Prev
    Next
    INDEX
    Explanations

    lump around, thrill of, freshwater sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alem
    0.40
    您的
    0.39
    㦣
    0.38
     descon
    0.37
    ിക്കാ
    0.37
    гур
    0.37
    itôt
    0.37
     tö
    0.36
     Sì
    0.35
     vệ
    0.35
    POSITIVE LOGITS
     initial
    0.49
    KT
    0.42
     inicial
    0.41
     rocks
    0.41
     Academic
    0.40
    <
    0.40
     Skin
    0.39
     iniziale
    0.38
     INITIAL
    0.38
     लिख
    0.38
    Activations Density 0.000%

    No Known Activations