© 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. 218776
    Prev
    Next
    INDEX
    Explanations

    send five thousand

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

    please, wait, achieve, Clients

    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
     pca
    0.46
    ᶦ
    0.46
     препят
    0.44
     paff
    0.44
    зда
    0.42
    肝
    0.42
     ПП
    0.41
    fY
    0.41
     latar
    0.41
    ..?
    0.40
    POSITIVE LOGITS
    㸸
    0.49
    ář
    0.46
     změ
    0.45
    ന
    0.45
    মী
    0.44
     কর্তৃত্ব
    0.44
    אל
    0.44
     Naomi
    0.44
    ersion
    0.44
    nam
    0.43
    Activations Density 0.001%

    No Known Activations