© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2540
    Prev
    Next
    INDEX
    Explanations

    java code

    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_40_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
     Canyon
    0.38
    োক
    0.37
     carcinogenic
    0.37
    ತರ
    0.37
    sqlite
    0.36
    馴
    0.36
    向量
    0.35
     PWMB
    0.35
     pluripotent
    0.35
    惯
    0.35
    POSITIVE LOGITS
    isBlank
    0.49
    assertThat
    0.47
    Java
    0.43
    assertEquals
    0.43
     assertThat
    0.43
    lombok
    0.43
     records
    0.43
    @
    0.42
     assertEquals
    0.42
    records
    0.42
    Activations Density 0.003%

    No Known Activations