© 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. 202087
    Prev
    Next
    INDEX
    Explanations

    assist or explain concepts

    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
     Regiment
    0.54
    ደም
    0.52
     sod
    0.47
    번
    0.47
    Созда
    0.46
    Structure
    0.46
    System
    0.46
     by
    0.45
     Settings
    0.45
    つ
    0.45
    POSITIVE LOGITS
    цей
    0.44
    ब्ल्यू
    0.44
    ren
    0.43
    PPtr
    0.43
    imet
    0.42
    president
    0.41
    }^{*}=
    0.41
     peeling
    0.41
    on
    0.40
    niers
    0.40
    Activations Density 0.001%

    No Known Activations