© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6812
    Prev
    Next
    INDEX
    Explanations

    mobile technology and devices

    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
    eda
    2.26
     daim
    2.22
    외부
    2.11
    defaults
    2.09
    외
    2.05
    zty
    2.05
    umni
    2.05
    eis
    2.03
    тения
    2.00
    edict
    1.96
    POSITIVE LOGITS
    >}</
    2.17
    (&:
    1.90
    fony
    1.83
    >|</
    1.79
    rscheinlich
    1.78
    Namara
    1.74
     непотпуним
    1.72
     adelante
    1.66
    先に
    1.66
     Naciones
    1.66
    Activations Density 0.028%

    No Known Activations