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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 9224
    Prev
    Next
    INDEX
    Explanations

    converting to decimal

    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_40_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
     Kan
    0.42
     (.
    0.38
     Jakob
    0.37
     jelent
    0.36
     Tune
    0.36
     Kü
    0.35
     oluşan
    0.35
    ྵ
    0.35
    व्ह
    0.35
     Vineyard
    0.35
    POSITIVE LOGITS
     decimal
    0.88
    decimal
    0.85
     decimals
    0.79
    Decimal
    0.74
     Decimal
    0.69
    decimals
    0.63
     DECIMAL
    0.61
    DEC
    0.58
    dec
    0.53
     déc
    0.52
    Activations Density 0.002%

    No Known Activations