© 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. 13401
    Prev
    Next
    INDEX
    Explanations

    person, particular, starts, will

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

    identifying a person or thing

    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
     부담
    0.43
    ങ്ങ
    0.43
    զ
    0.42
     सादर
    0.41
    Ժ
    0.41
     स्कैन
    0.41
    ąda
    0.40
     விவர
    0.40
     przepis
    0.40
    赠
    0.39
    POSITIVE LOGITS
     a
    0.57
     an
    0.50
     another
    0.47
     particular
    0.44
     this
    0.40
     one
    0.39
     човек
    0.39
     iemand
    0.38
     someone
    0.38
     bushes
    0.38
    Activations Density 0.000%

    No Known Activations