© 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. 128471
    Prev
    Next
    INDEX
    Explanations

    fingerprints clearly visible

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

    within a

    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
     homic
    0.45
     incest
    0.45
     तुम्ह
    0.44
     повин
    0.44
    lovepoetry
    0.44
    𝘆
    0.43
    binomial
    0.43
    AVI
    0.42
    comodule
    0.42
     (-\
    0.41
    POSITIVE LOGITS
    0.47
     Popper
    0.46
     The
    0.43
     onward
    0.42
     Django
    0.42
     nowrap
    0.42
    🤛
    0.42
     Suggestions
    0.41
    迄
    0.41
     Topeka
    0.41
    Activations Density 0.001%

    No Known Activations