© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 111606
    Prev
    Next
    INDEX
    Explanations

    specialize later

    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
     Dit
    0.38
     trail
    0.38
    琍
    0.36
    Aim
    0.36
    Heat
    0.35
    <0xB4>
    0.34
    Pres
    0.34
    Freedom
    0.34
    限
    0.34
    逆
    0.34
    POSITIVE LOGITS
     pierced
    0.45
     кантора
    0.45
     perforated
    0.44
     beğ
    0.44
    gled
    0.40
    TagName
    0.39
     pointillés
    0.38
    retirement
    0.38
     incapac
    0.38
     организма
    0.38
    Activations Density 0.000%

    No Known Activations