© 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. 137791
    Prev
    Next
    INDEX
    Explanations

    creative or group related entities

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

    technical and descriptive terms

    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
    レンタ
    0.47
     gravid
    0.47
    '
    0.46
     سات
    0.44
     fucking
    0.43
    口感
    0.42
     cortisol
    0.42
     dungeons
    0.41
    見
    0.41
     विक
    0.41
    POSITIVE LOGITS
     amacıyla
    0.55
    Cited
    0.52
    Author
    0.52
    Creative
    0.51
    Clique
    0.47
    Eco
    0.46
    arati
    0.45
     Akademie
    0.45
     creative
    0.44
    FRAM
    0.44
    Activations Density 0.000%

    No Known Activations