© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7021
    Prev
    Next
    INDEX
    Explanations

    defines bands or same as

    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_16k_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
     재
    0.41
     đặc
    0.39
     grammatical
    0.38
     neuromuscular
    0.38
     Known
    0.38
     antit
    0.38
     ciencia
    0.38
     motivational
    0.37
    রন
    0.37
     잘
    0.37
    POSITIVE LOGITS
     would
    0.68
    would
    0.68
     wären
    0.59
     habría
    0.56
     aurait
    0.55
     quedaría
    0.54
     auraient
    0.54
    nine
    0.53
     مثلا
    0.53
     serían
    0.53
    Activations Density 0.590%

    No Known Activations