© 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. 54127
    Prev
    Next
    INDEX
    Explanations

    diversified language context

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

    Magikarp, temporary, Echo, Barnaby

    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
     zostały
    0.48
     additionally
    0.47
     destroy
    0.47
     abnormally
    0.46
    s
    0.46
     decimals
    0.46
     podpis
    0.44
     initialized
    0.44
     intersect
    0.43
     moved
    0.43
    POSITIVE LOGITS
    iken
    0.49
    難
    0.48
    '];?>
    0.47
    資源
    0.46
    Diffuse
    0.46
     гиб
    0.45
     नीतियों
    0.45
    İK
    0.44
    ึก
    0.44
    adaptation
    0.44
    Activations Density 0.000%

    No Known Activations