© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52020
    Prev
    Next
    INDEX
    Explanations

    escaping hair, missiles, what is said

    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
    UP
    0.48
    τ
    0.48
    ح
    0.45
     (
    0.44
     UP
    0.44
    트
    0.42
    자기
    0.41
    ფ
    0.41
    ेर
    0.40
    رم
    0.40
    POSITIVE LOGITS
     Labrenzia
    0.55
    نګ
    0.54
    воды
    0.52
     Tutak
    0.52
    👓
    0.52
     underpin
    0.51
     keuken
    0.51
     kính
    0.50
     jenis
    0.49
     urbano
    0.49
    Activations Density 0.002%

    No Known Activations