© 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. 104246
    Prev
    Next
    INDEX
    Explanations

    Parking Reservations

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

    content and quote selection

    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
     harte
    0.52
          
    0.47
     toma
    0.46
    ↵↵
    0.46
    ه
    0.46
     Andes
    0.45
     totale
    0.45
     reine
    0.45
     metastases
    0.45
     fru
    0.45
    POSITIVE LOGITS
    ότητας
    0.45
    punct
    0.44
    gefunden
    0.42
    可能な
    0.42
    οδο
    0.42
    φων
    0.42
    াচিত
    0.41
    칭
    0.41
    TempVal
    0.41
    ISHING
    0.41
    Activations Density 0.001%

    No Known Activations