© 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. 155038
    Prev
    Next
    INDEX
    Explanations

    decide or help

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

    legal or code related to separators

    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
     刘
    0.56
     血
    0.55
     入っ
    0.54
    }).
    0.49
     劉
    0.49
     危
    0.49
    កំណ
    0.47
     પ્રમા
    0.46
    OLIS
    0.46
    ALLE
    0.46
    POSITIVE LOGITS
    ﻥ
    0.46
     скажу
    0.44
    javascript
    0.44
    غرب
    0.43
     decir
    0.42
     skyrock
    0.42
     تصمیم
    0.42
     terrain
    0.41
     enjoyable
    0.41
     марке
    0.41
    Activations Density 0.002%

    No Known Activations