© 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. 153601
    Prev
    Next
    INDEX
    Explanations

    places, amounts, or positions

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

    eliminate two

    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
    1
    0.51
     bestem
    0.48
    brewer
    0.46
    Day
    0.46
    Coat
    0.46
     guitarist
    0.45
    ईआरटी
    0.45
    Cob
    0.45
     Cob
    0.44
     scholar
    0.44
    POSITIVE LOGITS
    蛮
    0.46
     wedge
    0.44
    rset
    0.44
    方法的
    0.42
     kwargs
    0.42
     leaky
    0.41
     Xml
    0.41
    쐐
    0.41
     altering
    0.40
     wedges
    0.40
    Activations Density 0.000%

    No Known Activations