© 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. 1356
    Prev
    Next
    INDEX
    Explanations

    connecting concepts across languages

    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
     peninsula
    0.58
    تن
    0.47
    缈
    0.46
     ስ
    0.44
    라마
    0.44
     REPLACE
    0.44
    𒌓
    0.43
     ISLAND
    0.43
     dificuldades
    0.43
     trance
    0.43
    POSITIVE LOGITS
    of
    0.51
    रेल
    0.48
    蒸
    0.48
     कनेक्ट
    0.45
    ле
    0.44
    zac
    0.43
     connecting
    0.43
    つなが
    0.43
    బ్
    0.42
     Kogi
    0.42
    Activations Density 0.000%

    No Known Activations