© 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-65K
    7. 7620
    Prev
    Next
    INDEX
    Explanations

    negations and contrasts

    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_65k_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
     ditentukan
    0.43
     اگر
    0.41
     সূচনা
    0.41
     contraindicated
    0.40
     tow
    0.40
     *=
    0.39
     peremptory
    0.39
     bituminous
    0.39
     کردیا
    0.38
     glycine
    0.38
    POSITIVE LOGITS
     aviones
    0.50
    د
    0.49
    ással
    0.47
     objetos
    0.46
     данным
    0.46
    ラックス
    0.45
    фер
    0.45
     pantalones
    0.45
    ップ
    0.44
    ене
    0.44
    Activations Density 0.006%

    No Known Activations