Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 138198
    Prev
    Next
    INDEX
    Explanations

    RNA sequencing

    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_16_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
    וד
    0.54
    ни
    0.52
    ור
    0.48
    厲
    0.48
    וס
    0.46
     meu
    0.45
    וק
    0.45
    די
    0.44
    oui
    0.44
    <>());
    0.44
    POSITIVE LOGITS
    sigmaf
    0.54
     imme
    0.52
    浲
    0.52
    楖
    0.51
    炇
    0.51
     २००
    0.50
    साय
    0.50
     serían
    0.49
     памя
    0.49
     reiterate
    0.49
    Activations Density 0.000%

    No Known Activations