© 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-65K
    7. 8431
    Prev
    Next
    INDEX
    Explanations

    Series X, regression

    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_65k_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
     });
    0.47
     ఉంది
    0.45
    preliquidacion
    0.45
     każdej
    0.45
    赌场
    0.44
     varje
    0.44
     ठेवा
    0.44
    વી
    0.43
     zeich
    0.43
     schützen
    0.43
    POSITIVE LOGITS
    using
    0.49
    ?’
    0.49
    ’,
    0.47
    ’
    0.47
    FORD
    0.46
     malonyl
    0.46
    ,’
    0.45
    ју
    0.44
    сіб
    0.44
    ъ
    0.43
    Activations Density 0.015%

    No Known Activations