© 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. 189237
    Prev
    Next
    INDEX
    Explanations

    based on predictions

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

    transmitted to

    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
    મિ
    0.57
    𝐳
    0.54
    しろ
    0.53
    จึง
    0.52
    <0xA0>
    0.51
    nbhost
    0.51
    ૢ
    0.51
    暠
    0.51
    त्या
    0.50
    জি
    0.50
    POSITIVE LOGITS
     HIV
    0.54
     Cameroon
    0.54
    U
    0.46
    ’
    0.46
     Cambodia
    0.45
     despite
    0.45
     Karachi
    0.45
    </h4>
    0.44
    at
    0.44
     can
    0.44
    Activations Density 0.000%

    No Known Activations