© 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. 27732
    Prev
    Next
    INDEX
    Explanations

    members of a State

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

    all columns

    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
    ਮ
    0.60
    에서
    0.48
    잘
    0.45
    دود
    0.44
    下了
    0.44
    Verse
    0.42
    ز
    0.42
     ചെയ്യാ
    0.42
     قریب
    0.41
    해보
    0.40
    POSITIVE LOGITS
    rotz
    0.47
    icleta
    0.46
     licence
    0.45
    riction
    0.45
    ska
    0.44
    testng
    0.44
    ᱶ
    0.43
    ᕝ
    0.43
    ccedil
    0.43
    ူ
    0.43
    Activations Density 0.000%

    No Known Activations