© 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. 48874
    Prev
    Next
    INDEX
    Explanations

    languages and punctuation

    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
    甾
    0.47
     ম্যাচের
    0.46
     outperforms
    0.45
     daje
    0.44
    iyim
    0.44
     contrace
    0.42
     almeno
    0.42
     obtuvo
    0.41
     ου
    0.41
    ྨ
    0.41
    POSITIVE LOGITS
    Но
    0.45
    Other
    0.43
    New
    0.41
    Association
    0.41
    Communication
    0.40
    संदर्भ
    0.39
     szö
    0.39
     tornadoes
    0.39
     interpreters
    0.39
    Со
    0.39
    Activations Density 0.006%

    No Known Activations