© 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. 57505
    Prev
    Next
    INDEX
    Explanations

    general quality success

    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
    w
    0.51
    d
    0.49
    ρους
    0.47
     exploit
    0.47
    ץ
    0.46
    unlist
    0.45
    r
    0.44
    되
    0.44
    ｌ
    0.43
    лен
    0.43
    POSITIVE LOGITS
     ն
    0.47
     ayud
    0.45
     നേര
    0.41
    benar
    0.41
     జగ
    0.41
    onant
    0.41
     şimdi
    0.41
    rakt
    0.40
     göre
    0.40
    嘧
    0.40
    Activations Density 0.000%

    No Known Activations