© 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. 7935
    Prev
    Next
    INDEX
    Explanations

    parenthesized descriptions with labels

    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
     it
    0.52
     an
    0.45
     pā
    0.45
     lipids
    0.43
     cognition
    0.43
     precisely
    0.42
     versa
    0.42
    ْل
    0.41
     concatenation
    0.41
     potent
    0.41
    POSITIVE LOGITS
    4
    0.59
    圴
    0.57
    私が
    0.52
    3
    0.51
    jé
    0.50
    6
    0.50
    jk
    0.49
     ૩
    0.49
    ين
    0.48
    7
    0.48
    Activations Density 0.051%

    No Known Activations