© 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. 48036
    Prev
    Next
    INDEX
    Explanations

    ranking and finance context

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

    generating code and novel content

    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
     p
    0.56
     tested
    0.54
    rins
    0.52
    ira
    0.49
    ല്‍
    0.46
    ustellen
    0.46
    عادة
    0.46
    یرے
    0.45
    ના
    0.45
    Catagory
    0.45
    POSITIVE LOGITS
    댄
    0.49
    닌
    0.47
    letters
    0.46
     alloying
    0.42
     HOURS
    0.42
    літ
    0.41
    Letters
    0.41
     “[
    0.41
    lyrics
    0.41
     Alvarado
    0.41
    Activations Density 0.000%

    No Known Activations