© 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. 135345
    Prev
    Next
    INDEX
    Explanations

    Never forget

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

    workplace romance boundaries

    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
    </h3>
    0.48
     pili
    0.47
     Ω
    0.43
     fudge
    0.41
     plaint
    0.41
     piling
    0.41
     olds
    0.40
     vows
    0.40
    ([]
    0.39
     clots
    0.39
    POSITIVE LOGITS
    нга
    0.51
     кушымта
    0.51
     كومونز
    0.50
    Comunic
    0.47
    ccedil
    0.46
    交给
    0.46
     особливо
    0.45
    訲
    0.45
     Nahr
    0.45
    @[+][
    0.44
    Activations Density 0.000%

    No Known Activations