© 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. 209696
    Prev
    Next
    INDEX
    Explanations

    patient decided, colors and Adam go

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

    Old Man, though

    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
     parede
    0.51
    羋
    0.46
     кру
    0.45
     deixar
    0.45
    วงศ์
    0.45
     karna
    0.44
     CRUZ
    0.44
    羮
    0.44
    วรร
    0.44
     perju
    0.43
    POSITIVE LOGITS
    레스
    0.49
    </th>
    0.46
    جہ
    0.43
     શે
    0.43
    シェ
    0.42
    nickel
    0.42
    źni
    0.42
     ໜອງ
    0.42
    셰
    0.42
    페
    0.41
    Activations Density 0.001%

    No Known Activations