© 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. 78505
    Prev
    Next
    INDEX
    Explanations

    straightforward technical explanations

    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
    '
    0.52
    经济
    0.49
     א
    0.49
     zamknię
    0.48
    政府
    0.45
     கிராம
    0.45
    ANK
    0.45
    Ș
    0.45
    くる
    0.44
    economy
    0.44
    POSITIVE LOGITS
     Davey
    0.49
     Rolf
    0.48
     flavours
    0.48
     Patrick
    0.47
     Crocker
    0.46
     sprinting
    0.45
     Desmond
    0.44
     multiplets
    0.43
     Bolton
    0.43
    ihull
    0.43
    Activations Density 0.002%

    No Known Activations