© 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. 217668
    Prev
    Next
    INDEX
    Explanations

    stone crushers, quarry, pdf, youtube

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

    find paths

    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
     trafficking
    0.53
    č
    0.51
     legitim
    0.51
     mobil
    0.50
    lemens
    0.49
    ن
    0.48
    ನ
    0.47
     reparation
    0.46
    ruktur
    0.46
    रात
    0.46
    POSITIVE LOGITS
     '<
    0.47
    клары
    0.46
     '@
    0.45
    йдёт
    0.43
    ့်
    0.43
    getSeconds
    0.43
     "";
    0.42
     ""
    0.41
     "'
    0.41
    делить
    0.40
    Activations Density 0.001%

    No Known Activations