© 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. 15335
    Prev
    Next
    INDEX
    Explanations

    other side

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

    language, technical terms, and roles

    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
    聽
    0.53
    docs
    0.52
    薇
    0.46
     Apparently
    0.46
     December
    0.45
    財
    0.44
    ｜
    0.44
     Could
    0.43
    Could
    0.42
    也不知道
    0.42
    POSITIVE LOGITS
     اثنين
    0.52
    适合
    0.51
     äh
    0.49
     equipo
    0.49
     liturg
    0.49
     phù
    0.49
    yong
    0.48
    锭
    0.47
     해당하는
    0.47
     apresent
    0.47
    Activations Density 0.000%

    No Known Activations