© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 87033
    Prev
    Next
    INDEX
    Explanations

    words often followed by descriptions

    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_53_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
     deuterium
    0.43
     acoustic
    0.40
     ocul
    0.38
     san
    0.38
    发育
    0.38
     الس
    0.38
     zil
    0.37
    鹧
    0.37
     bar
    0.37
     বিবি
    0.37
    POSITIVE LOGITS
    Model
    0.46
    ospin
    0.43
     类型
    0.40
    Overflow
    0.40
    優勝
    0.39
     πίνακα
    0.39
     मॉडल
    0.39
     cháy
    0.39
    モデル
    0.38
     પ્રેમ
    0.38
    Activations Density 0.000%

    No Known Activations