© 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. 35034
    Prev
    Next
    INDEX
    Explanations

    across daytime realm have or role

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

    next element

    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
    เห
    0.44
     Puedes
    0.41
    唉
    0.41
    zynarod
    0.40
     ചൊ
    0.40
    erat
    0.40
     あれ
    0.40
     அங்க
    0.40
     Configuring
    0.40
     아름
    0.40
    POSITIVE LOGITS
    ।
    0.57
    '।
    0.48
    。
    0.47
    ική
    0.45
     conquist
    0.45
     jaw
    0.44
     handy
    0.44
    ।]
    0.44
     laborious
    0.42
    Clipboard
    0.41
    Activations Density 0.000%

    No Known Activations