© 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. 24077
    Prev
    Next
    INDEX
    Explanations

    language context

    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
     まず
    0.40
     pervasive
    0.38
     ಇರುವ
    0.38
     practiced
    0.37
     assorted
    0.36
    se
    0.36
    +
    0.36
     expansive
    0.36
     באמצע
    0.35
    warz
    0.35
    POSITIVE LOGITS
    ֥
    0.44
     यौन
    0.43
    ˈ
    0.43
     маркетин
    0.40
     уголов
    0.40
    热水
    0.40
    afood
    0.38
    맛집
    0.38
    南極
    0.37
    労働
    0.37
    Activations Density 0.036%

    No Known Activations