© 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. 30265
    Prev
    Next
    INDEX
    Explanations

    what they're

    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
     adoptive
    0.46
    င်း
    0.45
    Experienced
    0.45
    ות
    0.43
    രീ
    0.43
     سایټ
    0.42
    技术
    0.42
    ບ
    0.42
    ঞ
    0.41
     pronunciation
    0.40
    POSITIVE LOGITS
     зам
    0.49
    payer
    0.49
    ointed
    0.47
    els
    0.47
    
    0.46
    izzando
    0.46
     equ
    0.46
    attere
    0.46
    ysł
    0.45
     internazionale
    0.45
    Activations Density 0.003%

    No Known Activations