© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134535
    Prev
    Next
    INDEX
    Explanations

    exposure, filters, tree, seed

    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_40_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
    дове
    0.48
    ሆኑ
    0.42
    بوب
    0.42
    Debut
    0.40
     pursuit
    0.40
     طبي
    0.39
    忐
    0.39
    Tb
    0.39
     entrant
    0.39
    ลูกค้า
    0.38
    POSITIVE LOGITS
     [+]
    0.47
     Protocols
    0.41
     stirs
    0.39
     Shastri
    0.38
     protocols
    0.37
    铌
    0.37
     cinemat
    0.36
     Passwort
    0.36
    蟶
    0.35
    ریت
    0.35
    Activations Density 0.001%

    No Known Activations