© 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. 67534
    Prev
    Next
    INDEX
    Explanations

    most important instructions

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

    shapeshifting, morphing, wearing

    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
    发射
    0.49
    영화
    0.48
     Gerade
    0.46
     কালিক
    0.46
    宻
    0.45
    функ
    0.45
    箐
    0.45
     Accumulated
    0.45
    넣
    0.45
    特征
    0.44
    POSITIVE LOGITS
     stigma
    0.47
     alcoved
    0.44
     Gaulle
    0.44
     doorstep
    0.44
    it
    0.43
    atat
    0.42
     seafront
    0.42
    hotels
    0.42
    प्शन
    0.41
     nostrils
    0.41
    Activations Density 0.001%

    No Known Activations