© 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. 16360
    Prev
    Next
    INDEX
    Explanations

    I could speak

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

    explaining meanings

    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
    템
    0.41
    的地方
    0.38
    ಂತ್ರ
    0.38
    它们
    0.38
     beni
    0.38
     bases
    0.37
    নতুন
    0.37
    維
    0.37
    })^{
    0.36
    ␥
    0.36
    POSITIVE LOGITS
     obviously
    0.60
    obviously
    0.56
    这话
    0.56
    这句话
    0.54
     tentu
    0.52
     evidentemente
    0.52
     phrasing
    0.51
    presumably
    0.51
     worded
    0.50
     paraphr
    0.50
    Activations Density 0.152%

    No Known Activations