© 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. 222875
    Prev
    Next
    INDEX
    Explanations

    welcome, psychological factors, cravings

    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
    髂
    0.43
     מיט
    0.43
     месте
    0.42
     সত্যিকারের
    0.41
     besk
    0.40
     surfactant
    0.40
     partur
    0.39
     నిర్వ
    0.39
     followers
    0.39
     ubiquitous
    0.39
    POSITIVE LOGITS
     seules
    0.39
    communication
    0.39
    notes
    0.39
    (">
    0.38
    Tera
    0.38
    wir
    0.38
    MOT
    0.37
    omotor
    0.37
    uerung
    0.37
    yu
    0.37
    Activations Density 0.000%

    No Known Activations