© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7956
    Prev
    Next
    INDEX
    Explanations

    superlatives ending in est

    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
     numai
    0.28
     ：
    0.28
    ：
    0.28
     \
    0.27
    :,
    0.27
    muy
    0.27
    :**
    0.27
     narrates
    0.27
    >:
    0.26
     the
    0.26
    POSITIVE LOGITS
     imaginable
    0.55
     conceivable
    0.51
     possible
    0.48
     posible
    0.45
     możli
    0.44
    最有
    0.44
     cleanest
    0.44
     possível
    0.43
    iest
    0.42
    possible
    0.42
    Activations Density 0.055%

    No Known Activations