© 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. 177731
    Prev
    Next
    INDEX
    Explanations

    weekly flash

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

    Market and representation

    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
    Ꮸ
    0.53
    𝚍
    0.49
     밝
    0.49
    데이터
    0.49
    ("#{
    0.48
    ಹೆ
    0.47
    된
    0.47
    дер
    0.47
     cuisses
    0.47
    ៤
    0.47
    POSITIVE LOGITS
     presente
    0.56
    elle
    0.47
     MAC
    0.46
     is
    0.46
    ament
    0.44
    lew
    0.44
     aktuelle
    0.44
     rationale
    0.44
     Oral
    0.44
     MAX
    0.43
    Activations Density 0.000%

    No Known Activations