© 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. 243583
    Prev
    Next
    INDEX
    Explanations

    quality with

    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
    Powerful
    0.47
    roje
    0.47
    googleapis
    0.46
    interpretation
    0.45
    𝗻
    0.45
    𝘸
    0.44
    িপ্ত
    0.44
    ϊ
    0.43
     Powerful
    0.43
    వేయ
    0.43
    POSITIVE LOGITS
     plage
    0.50
     extinction
    0.49
    GONE
    0.47
     indem
    0.47
     residences
    0.46
     unscathed
    0.46
     actualización
    0.45
     plages
    0.45
     πλη
    0.45
     échelle
    0.45
    Activations Density 0.000%

    No Known Activations