© 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. 203269
    Prev
    Next
    INDEX
    Explanations

    functioning offline

    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
     vuelve
    0.46
     gerne
    0.45
     disple
    0.45
     bisa
    0.45
    惑
    0.45
     putea
    0.44
     ovoj
    0.43
     poslov
    0.43
     hrane
    0.43
     özel
    0.42
    POSITIVE LOGITS
    txt
    0.49
    r
    0.41
    timeout
    0.41
     CONTENT
    0.41
     Essence
    0.41
    lighter
    0.41
     закон
    0.41
     ONE
    0.40
     STONE
    0.40
     அட்ட
    0.40
    Activations Density 0.003%

    No Known Activations