© 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. 81302
    Prev
    Next
    INDEX
    Explanations

    your perspective, they went

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

    However

    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
    0.50
     startling
    0.50
     rigid
    0.50
     rapidly
    0.46
     cycl
    0.45
    1
    0.45
    7
    0.44
     heel
    0.43
     scattering
    0.43
    9
    0.43
    POSITIVE LOGITS
     言っ
    0.57
    vykor
    0.55
    enquête
    0.53
     तिजारत
    0.53
     思う
    0.50
     офі
    0.50
     これは
    0.50
    Arvore
    0.49
     auxqu
    0.48
     ھ
    0.48
    Activations Density 0.001%

    No Known Activations