© 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-65K
    7. 7940
    Prev
    Next
    INDEX
    Explanations

    measurements or instructions

    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
    何度も
    0.43
    たくさん
    0.41
    भा
    0.41
     அவை
    0.41
     अवस्था
    0.40
     произведение
    0.39
    ಮಗೆ
    0.39
    蕙
    0.39
     صبر
    0.38
    <unused1905>
    0.38
    POSITIVE LOGITS
    Index
    0.43
    ége
    0.42
     metoda
    0.41
     gelegt
    0.41
    ിലേ
    0.40
    ഡിയ
    0.40
     curator
    0.40
     lasci
    0.38
     animados
    0.38
    Deb
    0.38
    Activations Density 0.017%

    No Known Activations