© 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. 100
    Prev
    Next
    INDEX
    Explanations

    year sixty 20

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

    code, standards, and explanations

    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
    इए
    0.56
    धारी
    0.50
    นอก
    0.49
    믿
    0.47
    จำ
    0.46
    ා
    0.46
    ดูก
    0.44
    петров
    0.44
    ल
    0.44
     dubious
    0.43
    POSITIVE LOGITS
     giudice
    0.57
     qui
    0.52
     francia
    0.52
     στο
    0.52
     JFK
    0.51
     CCN
    0.48
     clinician
    0.47
     clinique
    0.47
     schizophrenia
    0.46
     one
    0.46
    Activations Density 0.000%

    No Known Activations