© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5875
    Prev
    Next
    INDEX
    Explanations

    how to install

    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
    nm
    1.29
    PRE
    1.05
    verd
    0.98
    可
    0.97
    NM
    0.97
    there
    0.97
    临
    0.97
    num
    0.95
    oooo
    0.93
    states
    0.92
    POSITIVE LOGITS
     [][]
    1.56
    ématiques
    1.56
    ('/',
    1.55
    ayeva
    1.53
    zonej
    1.52
    ahanga
    1.52
    estyle
    1.50
     #-}
    1.49
    Datei
    1.47
    berra
    1.47
    Activations Density 0.040%

    No Known Activations