© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136174
    Prev
    Next
    INDEX
    Explanations

    my<0xE2><0x80><0x85>boy

    np_acts-logits-general · gemini-2.5-flash-lite

    implied context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Supported
    0.47
    Reactive
    0.46
    썻
    0.45
    potentially
    0.42
    שור
    0.42
    Unified
    0.41
    Backed
    0.41
    果た
    0.40
    қ
    0.40
    Wedgwood
    0.40
    POSITIVE LOGITS
     '',
    0.47
     \\\
    0.44
     -\
    0.44
     although
    0.43
     muertos
    0.42
    َی
    0.42
     '.
    0.42
     为
    0.42
     causa
    0.41
     poiché
    0.41
    Activations Density 0.001%

    No Known Activations