© 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-262K
    7. 27937
    Prev
    Next
    INDEX
    Explanations

    form shall, domains tend, relationships can

    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
    plaf
    0.48
    fix
    0.47
    alogical
    0.46
    龈
    0.45
    plate
    0.45
    谦
    0.44
    thin
    0.43
    țe
    0.43
    licts
    0.43
    garde
    0.43
    POSITIVE LOGITS
     Rugby
    0.47
     sentiment
    0.45
     despite
    0.43
     attractive
    0.43
     stagnation
    0.42
     bytecode
    0.42
     BET
    0.42
     natomiast
    0.42
     M
    0.41
     sawdust
    0.41
    Activations Density 0.001%

    No Known Activations