© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143118
    Prev
    Next
    INDEX
    Explanations

    geographic locations and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite

    iOS, months, evolved, Olsen, Concerns, instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ене
    0.56
    ובה
    0.52
    াণ
    0.50
    ificante
    0.48
     fictitious
    0.47
     கவனம்
    0.47
    лізу
    0.47
    f
    0.47
    atthe
    0.46
    orschung
    0.46
    POSITIVE LOGITS
    Been
    0.45
    Mathematics
    0.43
    Nurse
    0.43
     discoveries
    0.42
    Tai
    0.42
    Drinking
    0.41
     springer
    0.40
    Shopping
    0.40
    Kak
    0.40
    Cal
    0.40
    Activations Density 0.001%

    No Known Activations