© 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. 197431
    Prev
    Next
    INDEX
    Explanations

    academic or formal settings

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

    ask users what they want

    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
    ademia
    0.52
    ಬಹುದು
    0.46
    Aligned
    0.45
     miễn
    0.44
    *$
    0.44
    microphone
    0.44
    aligned
    0.43
    ხვევ
    0.43
    govor
    0.42
    couple
    0.41
    POSITIVE LOGITS
    である
    0.52
    of
    0.50
     областях
    0.48
    र
    0.46
     Grenzen
    0.46
     tranquillity
    0.46
     格
    0.46
     απ
    0.45
    4
    0.45
    ר
    0.45
    Activations Density 0.001%

    No Known Activations