© 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. 32850
    Prev
    Next
    INDEX
    Explanations

    followed by specific words

    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
    thorace
    0.63
     או
    0.52
    🜨
    0.50
     possono
    0.49
     Хар
    0.48
    texto
    0.48
    synt
    0.48
    ultima
    0.48
    articolo
    0.48
     अभिय
    0.47
    POSITIVE LOGITS
     boasts
    0.48
    oirs
    0.44
     rails
    0.43
    嶆
    0.43
     Formerly
    0.42
     kotlin
    0.41
     लिरिक्स
    0.41
    从此
    0.39
    不仅仅
    0.39
     cloud
    0.39
    Activations Density 0.000%

    No Known Activations