© 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. 101088
    Prev
    Next
    INDEX
    Explanations

    another framework or provider

    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_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
    ∃
    0.51
     někol
    0.47
    酢
    0.47
    ាច់
    0.46
     då
    0.45
     calculi
    0.45
    assies
    0.45
     genug
    0.44
    ច្
    0.44
    、
    0.42
    POSITIVE LOGITS
    heri
    0.55
    u
    0.44
     रा
    0.43
     Keci
    0.43
     учителя
    0.43
    Ed
    0.43
     Lata
    0.42
     Armed
    0.41
     Ata
    0.41
    her
    0.41
    Activations Density 0.007%

    No Known Activations