© 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. 71879
    Prev
    Next
    INDEX
    Explanations

    web page, exactly, re solving

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

    descriptive words and abstract concepts

    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
     aquele
    0.53
     aquela
    0.52
    ᱖
    0.51
     aisl
    0.48
     pitanje
    0.48
    odob
    0.48
    quele
    0.48
     établir
    0.47
    例えば
    0.46
     slain
    0.46
    POSITIVE LOGITS
     ні
    0.49
     저희
    0.49
     면
    0.46
     활동
    0.44
    imer
    0.43
     뭔가
    0.42
    itty
    0.41
    logger
    0.41
     Grammy
    0.41
     아무
    0.40
    Activations Density 0.002%

    No Known Activations