© 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. 8480
    Prev
    Next
    INDEX
    Explanations

    comparative words followed by than

    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
     очень
    0.44
     بسیار
    0.43
    any
    0.42
     अत्यंत
    0.42
    ，
    0.41
    are
    0.40
     only
    0.40
     estremamente
    0.40
     zeer
    0.39
    0
    0.39
    POSITIVE LOGITS
     than
    1.12
     niż
    0.95
     decât
    0.91
    Than
    0.89
    than
    0.88
     kuin
    0.84
     Than
    0.81
     чем
    0.78
     ніж
    0.77
     než
    0.76
    Activations Density 0.711%

    No Known Activations