© 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. 165661
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    organizational structure or direction

    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
     watercolors
    0.47
    ++
    0.45
    zeczytaj
    0.43
     actuality
    0.42
     anul
    0.42
    oneg
    0.42
    jekte
    0.41
    Isa
    0.40
    كثر
    0.40
    дали
    0.40
    POSITIVE LOGITS
     φορά
    0.49
     이걸
    0.48
     LANC
    0.48
    ｘ
    0.47
    ELA
    0.46
     partai
    0.46
     सुमारे
    0.45
    ፍት
    0.45
     rostr
    0.44
     μαγγ
    0.44
    Activations Density 0.001%

    No Known Activations