© 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. 42019
    Prev
    Next
    INDEX
    Explanations

    research and review

    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
    Annot
    0.42
    Verse
    0.41
    Analyze
    0.40
    Balancer
    0.40
    Type
    0.40
    P
    0.40
    噻
    0.39
     epigen
    0.39
    V
    0.38
    Capability
    0.38
    POSITIVE LOGITS
    ا
    0.45
    átu
    0.43
    на
    0.43
    站
    0.42
     detay
    0.42
     Station
    0.41
     سقوط
    0.41
     Few
    0.41
     pentru
    0.41
    ąc
    0.40
    Activations Density 0.002%

    No Known Activations