© 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. 18961
    Prev
    Next
    INDEX
    Explanations

    starting, syntax, ST, Echo

    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
    addKill
    0.49
    𝟕
    0.46
    जरीवाल
    0.44
    ክል
    0.42
    ရင်
    0.41
    ्याम
    0.41
     hài
    0.41
     дете
    0.40
    ரியில்
    0.40
    ៧
    0.40
    POSITIVE LOGITS
     starts
    0.66
     comienza
    0.63
     beginnt
    0.60
     begins
    0.57
     beginnen
    0.55
     comenzar
    0.55
     começar
    0.55
     begint
    0.53
     start
    0.53
     startet
    0.52
    Activations Density 0.003%

    No Known Activations