© 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. 168650
    Prev
    Next
    INDEX
    Explanations

    huge riothealth risk appraisalslife recovery program

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

    brand names and technical terms

    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
    الأ
    0.53
     union
    0.52
    Glad
    0.52
    union
    0.51
    Influence
    0.48
    崞
    0.48
    را
    0.47
     textBox
    0.47
    تباط
    0.47
     Expansion
    0.46
    POSITIVE LOGITS
    áról
    0.52
    rás
    0.49
    iaj
    0.49
    nés
    0.48
    ā
    0.47
    apak
    0.46
    ṟ
    0.46
    ämp
    0.46
     senjata
    0.46
    ák
    0.45
    Activations Density 0.001%

    No Known Activations