© 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. 193673
    Prev
    Next
    INDEX
    Explanations

    brands and quality

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

    alkaline properties, erosion, progress, range

    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
    ónimo
    0.50
    명의
    0.42
     %#
    0.41
     जुड़
    0.40
     cierre
    0.40
    atini
    0.40
     MIDDLE
    0.39
    分离
    0.38
    霎
    0.38
    మంది
    0.38
    POSITIVE LOGITS
    }\}$.
    0.52
    常に
    0.49
     তোলে
    0.49
     expts
    0.48
    ه
    0.48
    \}$.
    0.47
     見
    0.46
     biocompat
    0.46
     prokary
    0.46
     impractic
    0.46
    Activations Density 0.000%

    No Known Activations