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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 123645
    Prev
    Next
    INDEX
    Explanations

    contrasting or qualifying information

    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
    ఎ
    0.52
     медицин
    0.51
    
    0.51
    இல்
    0.48
    새
    0.48
    समाचार
    0.48
    żliw
    0.47
     मेडिकल
    0.46
    <0x04>
    0.46
     புதிய
    0.46
    POSITIVE LOGITS
     perhaps
    0.48
     mutta
    0.44
     but
    0.43
     though
    0.41
     ;-)
    0.40
     understated
    0.39
     equally
    0.39
     JFK
    0.38
     But
    0.38
     aspects
    0.38
    Activations Density 0.010%

    No Known Activations