© 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. 29537
    Prev
    Next
    INDEX
    Explanations

    many advantages

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

    inside or on

    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
     或
    0.47
     ডিসেম্বর
    0.46
    种种
    0.45
    调研
    0.44
    或是
    0.44
     ricerche
    0.43
     democracy
    0.43
     investigaciones
    0.42
     dipende
    0.41
     বৎস
    0.41
    POSITIVE LOGITS
    е
    0.59
    ца
    0.58
    ческая
    0.55
    ма
    0.55
    in
    0.54
    ски
    0.54
    sq
    0.53
    ц
    0.53
    et
    0.53
    크
    0.53
    Activations Density 0.000%

    No Known Activations