© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    condensed matter physics

    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
    n
    0.85
    r
    0.69
    losses
    0.61
    d
    0.61
    g
    0.60
     bundles
    0.57
     Acids
    0.57
    ro
    0.56
    lers
    0.56
    </h2>
    0.55
    POSITIVE LOGITS
     traject
    0.54
    માં
    0.54
    𒉰
    0.53
     trajet
    0.52
     comport
    0.52
     које
    0.51
    のですが
    0.51
    واج
    0.51
    هاي
    0.51
    наў
    0.51
    Activations Density 0.000%

    No Known Activations