© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112344
    Prev
    Next
    INDEX
    Explanations

    group rate

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

    things customers

    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
    Coronavirus
    0.55
    A
    0.48
    '),
    0.44
    informatics
    0.44
     Coronavirus
    0.44
    ка
    0.43
     Electronics
    0.43
    Electronics
    0.42
    on
    0.42
    ATH
    0.42
    POSITIVE LOGITS
     luyện
    0.56
    𒌆
    0.55
     lateribus
    0.55
    StoredKeys
    0.49
     ditth
    0.49
     እድ
    0.49
     atend
    0.48
     presenceData
    0.48
    𒁀
    0.48
    renz
    0.47
    Activations Density 0.000%

    No Known Activations