© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6337
    Prev
    Next
    INDEX
    Explanations

    python code snippets

    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_12_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
    리카
    1.14
     vacuo
    1.12
    arum
    1.12
    リカ
    1.08
     Puri
    1.08
    憬
    1.08
    ヨー
    1.08
    วา
    1.07
     Sorrent
    1.07
    evi
    1.07
    POSITIVE LOGITS
     plato
    1.15
    '''
    1.12
     друз
    1.11
     platoon
    1.07
     Harding
    1.05
     """
    1.02
     Taft
    1.02
     '''
    1.02
    BrNO
    1.00
     Tk
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.