© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38978
    Prev
    Next
    INDEX
    Explanations

    regulation and information

    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
    сам
    0.47
     камер
    0.46
    drink
    0.43
    🐒
    0.42
    ≙
    0.42
     abused
    0.42
    сама
    0.42
     bebida
    0.42
    CND
    0.41
    প্রকার
    0.40
    POSITIVE LOGITS
    Dev
    0.47
    Ꮦ
    0.44
     شما
    0.41
     nantinya
    0.41
     ਤੁਸੀਂ
    0.39
     आपको
    0.39
     আপনাকে
    0.39
    .
    0.38
    沼
    0.38
    醞
    0.38
    Activations Density 0.005%

    No Known Activations