© 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. 65899
    Prev
    Next
    INDEX
    Explanations

    specific units and commands

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

    qualities of things

    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
    ავლ
    0.47
    Timothy
    0.46
     forgetting
    0.44
    িৎ
    0.43
    ὃ
    0.42
    ecek
    0.42
    耻
    0.41
    тят
    0.41
    Можно
    0.41
    比如說
    0.41
    POSITIVE LOGITS
     Secondo
    0.45
     epic
    0.44
     هستیم
    0.44
     oversized
    0.43
    AIRE
    0.43
    格外
    0.43
     EPC
    0.41
    ۗ
    0.41
     maig
    0.40
     ecc
    0.40
    Activations Density 0.002%

    No Known Activations