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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11541
    Prev
    Next
    INDEX
    Explanations

    leading to anger

    np_acts-logits-general · gemini-2.5-flash-lite

    Dynamic Island, DevOps practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subtypes
    0.45
    renamiento
    0.43
    쾰
    0.43
    ба
    0.42
     лі
    0.41
     cliquer
    0.41
    字符串
    0.41
    agen
    0.40
     okresie
    0.40
     escalate
    0.40
    POSITIVE LOGITS
    VIA
    0.50
     firmer
    0.47
    氿
    0.45
    μη
    0.45
     consuming
    0.44
     VIE
    0.44
     Nobody
    0.43
     Stakes
    0.43
    س
    0.43
    立場
    0.42
    Activations Density 0.000%

    No Known Activations