© 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. 11263
    Prev
    Next
    INDEX
    Explanations

    items described with a following noun or characteristic

    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
     HG
    0.42
     a
    0.39
     color
    0.39
     Swedish
    0.39
     the
    0.38
    heda
    0.38
     revolutionary
    0.37
     e
    0.37
     British
    0.37
     Da
    0.37
    POSITIVE LOGITS
    ঞ্জার
    0.47
     tiek
    0.45
    客厅
    0.44
     transcends
    0.43
    饌
    0.42
     содержит
    0.41
     underlies
    0.41
    EMPL
    0.40
    馔
    0.40
    زندگی
    0.40
    Activations Density 0.002%

    No Known Activations