© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138523
    Prev
    Next
    INDEX
    Explanations

    diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     રાશિ
    0.43
    ⊕
    0.43
     समी
    0.43
    nemonic
    0.42
    らす
    0.42
     மாநிலத்தில்
    0.41
    कु
    0.40
    iyeti
    0.40
     संगम
    0.40
    クー
    0.39
    POSITIVE LOGITS
    ⼀
    0.44
     drawers
    0.44
     kindergarten
    0.43
     vollständ
    0.43
     voldoende
    0.42
     extracts
    0.42
     powst
    0.42
     distribusi
    0.42
     congruence
    0.41
     fijn
    0.41
    Activations Density 0.010%

    No Known Activations