© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 212576
    Prev
    Next
    INDEX
    Explanations

    ascii letters

    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
     attended
    0.43
     Behavior
    0.42
     Moder
    0.38
     Manch
    0.38
    লস
    0.37
     interviewing
    0.37
    धक
    0.37
    ુ
    0.37
     Nicholas
    0.37
    裤
    0.36
    POSITIVE LOGITS
     hex
    0.44
    נגלית
    0.43
    hex
    0.40
     hexa
    0.40
     radial
    0.40
     ruta
    0.39
     mysteries
    0.38
    uriken
    0.38
     dihedral
    0.38
    んだ
    0.37
    Activations Density 0.000%

    No Known Activations