© 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. 168443
    Prev
    Next
    INDEX
    Explanations

    financial companies

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

    expansion will continue

    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
    Acceleration
    0.48
    速度
    0.46
    কেও
    0.46
    .
    0.45
    $.
    0.45
    時
    0.44
    it
    0.44
    加速
    0.42
    pps
    0.41
     tốc
    0.40
    POSITIVE LOGITS
     Señor
    0.49
     வன
    0.48
     Votre
    0.48
     Sé
    0.47
     Gemüse
    0.47
     París
    0.47
     Ganesh
    0.47
     Barça
    0.46
     Secretaría
    0.46
    Sé
    0.46
    Activations Density 0.001%

    No Known Activations