© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46148
    Prev
    Next
    INDEX
    Explanations

    fluid, different areas, specific tasks

    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_31_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
    starts
    0.47
    2
    0.45
     starts
    0.42
    8
    0.42
    s
    0.42
     announces
    0.41
    7
    0.41
     с
    0.41
    4
    0.41
    6
    0.40
    POSITIVE LOGITS
    yyati
    0.50
    ádiz
    0.50
    DbType
    0.48
     immersing
    0.48
     wygl
    0.46
    yatiti
    0.44
    🍛
    0.43
     auricular
    0.42
     instytuc
    0.42
    🍮
    0.42
    Activations Density 0.006%

    No Known Activations