© 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. 121753
    Prev
    Next
    INDEX
    Explanations

    OBDII compatible, sin of, support them

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

    explaining concepts or terms

    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
    د
    0.45
    ἢ
    0.44
    ,
    0.44
     направления
    0.43
     demikian
    0.43
     Avan
    0.43
    p
    0.43
    #,
    0.43
    יי
    0.42
     envisaged
    0.42
    POSITIVE LOGITS
     तक्र
    0.58
     リュ
    0.52
     치료
    0.48
     लियो
    0.48
    のカ
    0.48
     इंच
    0.47
     훨씬
    0.46
     CONDUCT
    0.46
    ギター
    0.45
     ಲೋ
    0.45
    Activations Density 0.000%

    No Known Activations