© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10788
    Prev
    Next
    INDEX
    Explanations

    footprints and prints

    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
     verbally
    0.43
    δικ
    0.41
     hostility
    0.41
    🔌
    0.39
    攞
    0.38
     financ
    0.38
     absurdity
    0.38
     financing
    0.38
     financiar
    0.38
     قناه
    0.38
    POSITIVE LOGITS
     imprint
    0.86
     footprints
    0.82
     footprint
    0.79
     fingerprint
    0.79
    痕
    0.77
     imprinted
    0.77
    跡
    0.69
     fingerprints
    0.67
    迹
    0.66
    prints
    0.65
    Activations Density 0.035%

    No Known Activations