© 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. 7821
    Prev
    Next
    INDEX
    Explanations

    respectively, where, which

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

    . :

    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
     ග
    0.40
     Agro
    0.38
    loadConst
    0.37
     Darmstadt
    0.37
    <unused689>
    0.36
     ऑयल
    0.36
     fè
    0.36
    स्थ्य
    0.35
     කාල
    0.35
    <unused1036>
    0.35
    POSITIVE LOGITS
    where
    0.43
    respectively
    0.43
    helping
    0.42
    ↵↵
    0.42
    which
    0.42
    compared
    0.42
    cannot
    0.39
    .\
    0.39
    以外の
    0.38
    except
    0.38
    Activations Density 0.075%

    No Known Activations