© 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. 179324
    Prev
    Next
    INDEX
    Explanations

    Rapture: founded to be

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

    surprisingly clean

    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
     kategor
    0.47
     layoffs
    0.47
    <{},
    0.46
     avaient
    0.46
     आणि
    0.45
     downsizing
    0.45
     stim
    0.44
     看
    0.44
     interstitiis
    0.44
     ଏ
    0.44
    POSITIVE LOGITS
    فیر
    0.41
    빗
    0.40
    mitting
    0.40
    他也
    0.39
    выше
    0.39
    ysteine
    0.39
    нили
    0.39
    անում
    0.39
    <0x0D>
    0.38
    ത്ര
    0.38
    Activations Density 0.001%

    No Known Activations