© 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. 244276
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

    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
    鴟
    0.49
    羮
    0.46
    膾
    0.46
    vertebr
    0.46
    欷
    0.45
    鍖
    0.43
    等の
    0.42
    汝
    0.42
    蓴
    0.42
    機械
    0.42
    POSITIVE LOGITS
     Nisha
    0.42
     Cryptocurrency
    0.41
     asks
    0.41
    ión
    0.41
     symptoms
    0.41
     Montoya
    0.41
     drawback
    0.40
     simplement
    0.40
     merely
    0.40
    нтэр
    0.39
    Activations Density 0.000%

    No Known Activations