© 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. 135897
    Prev
    Next
    INDEX
    Explanations

    hunting nature enemies trivia letters

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

    Relative Stability, Green door, Mint, high net

    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
     Instrum
    0.52
    끝
    0.48
    राक
    0.47
    ends
    0.46
     playerCards
    0.46
    ్రు
    0.45
    ರ್ಷ
    0.45
     jogos
    0.44
    endus
    0.44
    觸
    0.44
    POSITIVE LOGITS
     beautifully
    0.53
     hike
    0.52
     hiked
    0.49
     crawled
    0.48
     downgrade
    0.46
     lighting
    0.43
     nicely
    0.43
     herbal
    0.43
     facilitated
    0.43
     mysteriously
    0.42
    Activations Density 0.002%

    No Known Activations