© 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. 244215
    Prev
    Next
    INDEX
    Explanations

    children, house, Matrix

    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
     tweeted
    0.43
    了吗
    0.42
     texted
    0.42
     triggered
    0.42
     geographies
    0.42
     gets
    0.41
     descriptor
    0.41
    ဈ
    0.41
    #############
    0.41
     আজকে
    0.41
    POSITIVE LOGITS
     Fuerza
    0.44
    voice
    0.44
    amsmath
    0.43
     विरोधी
    0.43
    grabbing
    0.43
    하며
    0.42
     कार्यकर्ते
    0.42
     Enseñ
    0.42
     ክብ
    0.42
     จับ
    0.41
    Activations Density 0.000%

    No Known Activations