© 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. 244375
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     perdu
    0.51
    OutSize
    0.51
    די
    0.48
     тру
    0.46
    }^{+}\
    0.46
    conservation
    0.45
     conserved
    0.45
     }-\
    0.45
    ний
    0.44
    ді
    0.44
    POSITIVE LOGITS
     завое
    0.46
     EN
    0.45
     كريم
    0.44
     Join
    0.44
     Fill
    0.42
     Roop
    0.42
    تمي
    0.42
    anime
    0.42
     ज्वाइन
    0.42
    ro
    0.42
    Activations Density 0.001%

    No Known Activations