© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3383
    Prev
    Next
    INDEX
    Explanations

    asking for specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    來講
    1.18
    BYTE
    1.13
    sensors
    1.07
    pied
    0.99
     intents
    0.98
    omized
    0.97
    etics
    0.94
     }^{*}
    0.93
    として
    0.93
    pads
    0.93
    POSITIVE LOGITS
     favourite
    1.87
     fave
    1.85
     favorite
    1.80
     favorito
    1.56
     favourites
    1.55
     favorites
    1.49
     FAVOR
    1.47
    favorite
    1.44
     nickname
    1.42
     Lieblings
    1.39
    Activations Density 0.304%

    No Known Activations