© 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. 33213
    Prev
    Next
    INDEX
    Explanations

    self in Rust code

    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
     বৃহত্তর
    0.39
    გორ
    0.39
    氙
    0.38
     μέ
    0.37
    珈
    0.36
    荖
    0.36
    မာ
    0.36
     所
    0.36
    φέρ
    0.35
    ברים
    0.35
    POSITIVE LOGITS
     troubled
    0.40
     unlawfully
    0.36
     Rolex
    0.36
     famosos
    0.36
     Toyota
    0.35
     Motorsport
    0.35
     Srps
    0.34
     Einsatz
    0.34
     giro
    0.34
    ying
    0.34
    Activations Density 0.001%

    No Known Activations