© 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. 32527
    Prev
    Next
    INDEX
    Explanations

    specific words or code structures

    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
    
    0.44
     небольшой
    0.41
    ⎙
    0.40
    ጷ
    0.38
     westerly
    0.37
     statistiques
    0.37
    击
    0.37
    还是很
    0.36
     寸
    0.36
     риск
    0.36
    POSITIVE LOGITS
    got
    0.41
     Mam
    0.40
     managed
    0.40
    HF
    0.38
    zeug
    0.37
     manage
    0.37
     creates
    0.36
    Dom
    0.36
    lyan
    0.36
     samtidig
    0.36
    Activations Density 0.000%

    No Known Activations