© 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. 84649
    Prev
    Next
    INDEX
    Explanations

    limited or practical constraints

    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
     On
    0.52
     Maybe
    0.50
     at
    0.50
     Express
    0.49
     A
    0.48
     on
    0.48
    antum
    0.47
     by
    0.47
     .
    0.47
     Before
    0.47
    POSITIVE LOGITS
    𒊑
    0.50
    punkte
    0.49
    ังกฤษ
    0.48
    Maur
    0.47
    NaOMe
    0.47
    Contributions
    0.47
    செ
    0.47
     esclav
    0.46
    𐰤
    0.46
    ரோ
    0.46
    Activations Density 0.006%

    No Known Activations