© 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. 42074
    Prev
    Next
    INDEX
    Explanations

    tech and hardware components

    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
     begrij
    0.49
    ensatz
    0.46
    מבר
    0.44
    Hãy
    0.44
    欤
    0.44
    आपने
    0.43
    আপনি
    0.42
    してみてください
    0.42
    躏
    0.42
    mitz
    0.41
    POSITIVE LOGITS
     is
    0.48
     sub
    0.48
     were
    0.46
     geology
    0.45
     vody
    0.44
     itself
    0.43
    Tech
    0.43
     geography
    0.42
     installer
    0.42
     високо
    0.42
    Activations Density 0.002%

    No Known Activations