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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49149
    Prev
    Next
    INDEX
    Explanations

    concepts and future possibilities

    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
    함
    0.58
    দাম
    0.57
     poslov
    0.54
     febbraio
    0.53
     individuo
    0.53
     этом
    0.52
     кантип
    0.52
     мое
    0.51
     necesito
    0.51
    н
    0.51
    POSITIVE LOGITS
     proliferation
    0.52
     Proceedings
    0.51
     Steelers
    0.50
     lesion
    0.49
     Stations
    0.48
     Publications
    0.47
     shell
    0.47
     Shell
    0.46
     concave
    0.45
    Shell
    0.45
    Activations Density 0.003%

    No Known Activations