© 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. 51872
    Prev
    Next
    INDEX
    Explanations

    specific entities and 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
    шат
    0.51
    лаве
    0.49
    வார்
    0.48
    ῴ
    0.47
    бль
    0.47
    *>
    0.46
    継
    0.46
     lésions
    0.46
    炀
    0.46
    ität
    0.46
    POSITIVE LOGITS
    Forest
    0.47
     on
    0.45
     by
    0.45
    0
    0.44
    ă
    0.44
     encara
    0.44
     varios
    0.43
    cious
    0.43
    forestry
    0.42
    emb
    0.42
    Activations Density 0.000%

    No Known Activations