© 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-65K
    7. 54386
    Prev
    Next
    INDEX
    Explanations

    Target audience, directly, frameworks

    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_65k_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
    cido
    0.55
    toys
    0.50
    ce
    0.49
    <unused988>
    0.48
     objeto
    0.48
     gentile
    0.47
    tos
    0.47
    cookbook
    0.46
    OT
    0.46
    ILL
    0.46
    POSITIVE LOGITS
     Tension
    0.47
     terlibat
    0.46
     Barriers
    0.44
     materias
    0.42
     ters
    0.42
     tension
    0.41
     bakalım
    0.41
    洒
    0.40
     Prozess
    0.40
     клас
    0.40
    Activations Density 0.003%

    No Known Activations