© 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. 6704
    Prev
    Next
    INDEX
    Explanations

    describing states or qualities

    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
    ne
    0.54
    ל
    0.52
    ن
    0.50
    е
    0.50
    ר
    0.49
    内
    0.49
    ב
    0.49
    ل
    0.49
    lo
    0.48
    w
    0.48
    POSITIVE LOGITS
    mainframe
    0.50
     এদেশে
    0.45
     topography
    0.45
    Scoped
    0.43
    estamp
    0.41
    Hf
    0.41
     terjadinya
    0.41
     paci
    0.41
     sunsets
    0.41
     melanjutkan
    0.41
    Activations Density 0.000%

    No Known Activations