© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    objective journalism

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

    YouTube links

    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
    ৯০
    0.30
     بعدی
    0.26
    های
    0.26
     المستخدم
    0.25
    强调
    0.25
    ගත්
    0.24
     hexadecimal
    0.24
    㑬
    0.24
     عناصر
    0.24
     مارچ
    0.24
    POSITIVE LOGITS
    W
    0.26
    P
    0.25
    Y
    0.25
    Eff
    0.24
    Dy
    0.24
     J
    0.24
    Py
    0.24
     vyh
    0.24
    Torch
    0.23
    Bou
    0.23
    Activations Density 0.005%

    No Known Activations