© 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. 31-GEMMASCOPE-2-RES-65K
    7. 41038
    Prev
    Next
    INDEX
    Explanations

    concrete examples and specific applications

    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
     подар
    0.43
    赈
    0.42
    ካት
    0.41
     випад
    0.40
    <unused2042>
    0.40
    bett
    0.40
    さり
    0.40
    নং
    0.39
    soldiers
    0.39
    glicherweise
    0.39
    POSITIVE LOGITS
    4
    0.45
     tyrosine
    0.41
     pathogenic
    0.40
     superfamily
    0.40
    indeer
    0.40
     astrophys
    0.40
     HOMO
    0.39
    eus
    0.39
    Functional
    0.39
     hlad
    0.39
    Activations Density 0.016%

    No Known Activations