© 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. 52699
    Prev
    Next
    INDEX
    Explanations

    North Carolina, tensile

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

    discussion of "fascinating" or "unrealistic"

    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
    Wrist
    0.47
     hadronic
    0.46
    Thin
    0.43
     ripples
    0.42
     بک
    0.41
     compound
    0.41
     힘
    0.40
     cơn
    0.40
    ASCADE
    0.40
     palsy
    0.40
    POSITIVE LOGITS
    charAt
    0.47
     Pursuant
    0.45
    mysqli
    0.44
     Usuario
    0.44
    ukat
    0.44
    currentTime
    0.43
    utilisateur
    0.43
    centaje
    0.43
     कायद्या
    0.43
    '][$
    0.42
    Activations Density 0.000%

    No Known Activations