© 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. 143840
    Prev
    Next
    INDEX
    Explanations

    binary software components

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

    oral disclosures and software distribution

    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
    }+
    0.50
     }+
    0.47
     ہزار
    0.47
     اینجا
    0.45
     این
    0.45
    ها
    0.44
     Styling
    0.44
     이게
    0.44
    ގ
    0.43
    这段
    0.42
    POSITIVE LOGITS
     visant
    0.38
     популя
    0.38
    GB
    0.37
     Authorized
    0.37
     trazendo
    0.37
     фай
    0.37
     بحيث
    0.37
     Invoke
    0.36
     produto
    0.36
     случай
    0.36
    Activations Density 0.001%

    No Known Activations