© 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. 245736
    Prev
    Next
    INDEX
    Explanations

    cleaner, angular outlines

    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
    0.54
     ఉపయోగ
    0.49
    āl
    0.44
    鸬
    0.43
    ApiClient
    0.43
    IfNeeded
    0.42
    อฟ
    0.41
     Количество
    0.40
     ላ
    0.40
    Roboto
    0.40
    POSITIVE LOGITS
     discrep
    0.60
     sorprend
    0.57
     absurd
    0.56
     scandalous
    0.56
     frivolous
    0.54
     ತೋರಿಸ
    0.53
     rilev
    0.52
     slogans
    0.52
     rankings
    0.51
     conjectures
    0.50
    Activations Density 0.002%

    No Known Activations