© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 324
    Prev
    Next
    INDEX
    Explanations

    the importance

    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
     delas
    1.13
    ahkan
    1.11
     coer
    1.09
    rie
    1.08
    érer
    1.05
    udie
    1.04
    ར
    1.04
     depending
    1.03
     *.
    1.03
    alé
    1.03
    POSITIVE LOGITS
     twentieth
    1.60
     seventies
    1.52
     nineties
    1.52
     late
    1.51
     beginnings
    1.51
     nineteenth
    1.51
     eighties
    1.46
     sixties
    1.43
     Twentieth
    1.42
     inception
    1.41
    Activations Density 3.364%

    No Known Activations