© 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-262K
    7. 138381
    Prev
    Next
    INDEX
    Explanations

    Assessing or highlighting existence or visibility

    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
     waahanga
    0.46
     Augusto
    0.42
     Oahu
    0.41
    ko
    0.40
    akkhati
    0.40
    ҝ
    0.40
     etkin
    0.39
    st
    0.39
     Attic
    0.39
    arı
    0.39
    POSITIVE LOGITS
    ັນ
    0.53
    永
    0.50
     rende
    0.48
     друг
    0.48
     со
    0.47
     stakeholders
    0.47
     stakeholder
    0.46
     て
    0.45
    雞
    0.44
     cette
    0.44
    Activations Density 0.010%

    No Known Activations