© 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-262K
    7. 204165
    Prev
    Next
    INDEX
    Explanations

    common descriptive words

    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
    T
    0.49
    Results
    0.49
    R
    0.46
    Y
    0.46
    Result
    0.43
    J
    0.41
    Dynamic
    0.40
    结果
    0.39
    套
    0.39
     Harlan
    0.39
    POSITIVE LOGITS
     TOWN
    0.49
    шего
    0.48
     விரும்ப
    0.47
    ặng
    0.47
     dividir
    0.46
     Dezember
    0.46
     milion
    0.46
    ཋ
    0.46
    𝔦
    0.46
     privée
    0.45
    Activations Density 0.006%

    No Known Activations