© 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. 214273
    Prev
    Next
    INDEX
    Explanations

    functions, states, or properties

    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
    But
    0.41
    image
    0.39
    And
    0.39
    typedef
    0.38
    <
    0.38
     fires
    0.37
    getDefault
    0.37
    google
    0.37
    aredo
    0.37
     vinegar
    0.37
    POSITIVE LOGITS
     فونٹ
    0.47
     personer
    0.43
    的态度
    0.41
     sikap
    0.40
     xong
    0.39
     berfungsi
    0.39
     ڈاؤن
    0.38
     deve
    0.38
     nuove
    0.38
    譲
    0.38
    Activations Density 0.000%

    No Known Activations