© 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. 111328
    Prev
    Next
    INDEX
    Explanations

    finding things out

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

    building blocks and products

    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
    宓
    0.49
     वित्तीय
    0.49
     perfumes
    0.49
    ativas
    0.47
     opções
    0.46
    fixtures
    0.46
    邇
    0.45
     frm
    0.44
     soluções
    0.44
    七
    0.44
    POSITIVE LOGITS
    ?»
    0.51
     centrifugal
    0.51
    pa
    0.47
    Cent
    0.47
     Centennial
    0.45
    $/.
    0.44
    ？」
    0.44
    »:
    0.44
     statesmen
    0.44
    ⁍
    0.44
    Activations Density 0.000%

    No Known Activations