© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86789
    Prev
    Next
    INDEX
    Explanations

    physical properties of liquids

    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_16_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
     זו
    0.77
    Despatx
    0.76
    <bbox>
    0.75
    রের
    0.74
     нём
    0.70
    ماً
    0.68
     povos
    0.67
    ScriptBuf
    0.67
     deli
    0.66
     أو
    0.66
    POSITIVE LOGITS
    g
    1.17
    s
    1.16
    y
    1.13
    1
    1.07
    t
    1.02
    f
    0.93
    ar
    0.89
    ur
    0.86
    ni
    0.85
    in
    0.84
    Activations Density 0.002%

    No Known Activations