© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9828
    Prev
    Next
    INDEX
    Explanations

    common noun pairings

    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_16k_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
     and
    0.39
    ー
    0.39
    си
    0.36
    <0xE1>
    0.35
    у
    0.35
    ד
    0.34
    з
    0.33
    ի
    0.33
    ци
    0.32
    ኵ
    0.32
    POSITIVE LOGITS
     uncorrelated
    0.37
     ஒரு
    0.34
     KeyError
    0.34
     plausible
    0.34
     violated
    0.33
     tentatively
    0.33
     somewhat
    0.33
     దాని
    0.32
     inferred
    0.32
     distraught
    0.31
    Activations Density 0.277%

    No Known Activations