© 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. 204328
    Prev
    Next
    INDEX
    Explanations

    gift certificate

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

    comprehensive psychiatric evaluation

    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
     médicale
    0.56
    uvos
    0.55
    řich
    0.54
     الطل
    0.53
     Ferté
    0.52
     Ă
    0.50
     пище
    0.50
     guter
    0.50
    ęć
    0.50
     malos
    0.50
    POSITIVE LOGITS
    IS
    0.55
    Okay
    0.53
    స్త
    0.50
    Jessica
    0.50
    ה
    0.49
    Additionally
    0.49
    大家好
    0.49
    Z
    0.49
    Northern
    0.48
    Jennifer
    0.48
    Activations Density 0.000%

    No Known Activations