© 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. 15576
    Prev
    Next
    INDEX
    Explanations

    preferences and recommendations

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

    explaining alternatives instead

    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
    肢
    0.46
    годні
    0.46
    🈺
    0.45
    աս
    0.45
    檐
    0.45
    俎
    0.44
    ા
    0.44
    iculture
    0.44
    asakan
    0.43
    ബോ
    0.43
    POSITIVE LOGITS
     tls
    0.46
    tls
    0.46
     versión
    0.45
    ’
    0.43
     compléter
    0.42
     versions
    0.42
     Estos
    0.41
     Tried
    0.41
     These
    0.41
     cnt
    0.41
    Activations Density 0.000%

    No Known Activations