© 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. 27607
    Prev
    Next
    INDEX
    Explanations

    highlighting sections or points

    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
    糍
    0.52
    annels
    0.51
    otin
    0.50
    ographics
    0.49
     hộ
    0.49
    illery
    0.48
     হইয়৷
    0.46
    uded
    0.45
    स्टेंस
    0.44
     Bedi
    0.43
    POSITIVE LOGITS
     justific
    0.58
     inver
    0.51
     destac
    0.49
     capit
    0.49
     creación
    0.48
     connexion
    0.48
     reprise
    0.47
    つ
    0.46
     literal
    0.46
     capitalizing
    0.46
    Activations Density 0.003%

    No Known Activations