© 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. 129261
    Prev
    Next
    INDEX
    Explanations

    wave whose, change, grow, square channel, grace is

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

    affects girls; originally; saw; complex

    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
     pleasurable
    0.49
     நெரு
    0.45
     psychic
    0.43
     sanguine
    0.42
    昼
    0.41
     COVER
    0.41
    TUB
    0.41
    ೊ
    0.41
     daytime
    0.40
    ұ
    0.40
    POSITIVE LOGITS
     liga
    0.55
     Integr
    0.52
    hang
    0.51
     integra
    0.49
     teorie
    0.49
     pouvaient
    0.48
     Liga
    0.48
     integ
    0.48
     integr
    0.47
     kall
    0.47
    Activations Density 0.000%

    No Known Activations