© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 23464
    Prev
    Next
    INDEX
    Explanations

    false positives and negatives

    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_all/layer_41_width_262k_l0_big
    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
    uche
    0.40
    ৈ
    0.39
    醅
    0.38
    slider
    0.37
    дзе
    0.36
    Numeral
    0.36
    ણી
    0.35
    Gé
    0.35
    审
    0.34
    usse
    0.34
    POSITIVE LOGITS
     positive
    2.73
     Positive
    2.50
    Positive
    2.41
    positive
    2.34
     positiva
    2.23
     positif
    2.22
     positivo
    2.20
     positives
    2.19
     pozitiv
    2.16
     positivos
    2.14
    Activations Density 0.005%

    No Known Activations