© 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. 53477
    Prev
    Next
    INDEX
    Explanations

    satellites orbiting

    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
    ненно
    0.46
     Genau
    0.44
    이에
    0.41
    คโน
    0.40
     newsletters
    0.39
    ieszka
    0.39
    ösungen
    0.39
    ต
    0.38
    …]
    0.38
     dares
    0.38
    POSITIVE LOGITS
     bumi
    0.50
     u
    0.49
     g
    0.49
     adaptación
    0.48
     V
    0.47
     contesto
    0.47
     السيا
    0.47
     रोशनी
    0.47
     pril
    0.46
    hydration
    0.46
    Activations Density 0.000%

    No Known Activations