© 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. 88447
    Prev
    Next
    INDEX
    Explanations

    online and web services

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

    scale, cracks, visually, width, size, description

    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
    saldo
    0.53
    tdown
    0.52
     يون
    0.51
    už
    0.50
     కృషి
    0.49
     आवेद
    0.48
     හෝ
    0.47
    <unused626>
    0.47
    <unused634>
    0.46
     كتابه
    0.46
    POSITIVE LOGITS
    ϋ
    0.47
    <i>
    0.46
    
    0.44
    幕
    0.44
    ᴇ
    0.44
    otted
    0.43
    ำ
    0.43
    <em>
    0.43
    <b>
    0.42
     Annual
    0.42
    Activations Density 0.000%

    No Known Activations