© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204076
    Prev
    Next
    INDEX
    Explanations

    access through

    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
    `),
    0.43
    賚
    0.41
    »),
    0.41
    behaved
    0.41
    ブ
    0.40
     sculpture
    0.39
     fest
    0.39
     terão
    0.39
     halluc
    0.38
    )
    0.38
    POSITIVE LOGITS
     নোট
    0.46
    sgál
    0.45
     Υ
    0.44
     oferty
    0.42
     Revisited
    0.42
    som
    0.42
     পূর্ববাংলার
    0.42
     Tentang
    0.42
    scriptsize
    0.42
    PMS
    0.41
    Activations Density 0.002%

    No Known Activations