© 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. 54960
    Prev
    Next
    INDEX
    Explanations

    pre- event or state

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

    pre- followed by a concept or event

    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
    相应的
    0.47
    issä
    0.45
    a
    0.43
     없다
    0.42
    flächen
    0.42
     ㄴ
    0.41
    nbr
    0.41
    ettha
    0.41
     ，
    0.41
     만큼
    0.41
    POSITIVE LOGITS
     estranged
    0.48
     interrump
    0.46
     apartheid
    0.44
     intimidated
    0.44
     persecuted
    0.43
    那我們
    0.43
     immigrated
    0.43
     incarcer
    0.42
     devout
    0.42
     necessariamente
    0.42
    Activations Density 0.021%

    No Known Activations