© 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. 198351
    Prev
    Next
    INDEX
    Explanations

    party packages

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

    ForeignKey to

    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
    েরই
    0.54
    ün
    0.52
    >:
    0.52
     contigo
    0.49
    ozems
    0.48
    ┳
    0.47
     useParams
    0.46
    ?>"
    0.46
    은
    0.46
     شرطونو
    0.45
    POSITIVE LOGITS
    ни
    0.53
     गिरावट
    0.44
    intervention
    0.44
     secur
    0.44
    biased
    0.43
    Salut
    0.43
    udukan
    0.43
     audible
    0.42
    Declar
    0.42
     Alter
    0.41
    Activations Density 0.000%

    No Known Activations