© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14007
    Prev
    Next
    INDEX
    Explanations

    feelings of guilt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    een
    3.05
    ة
    2.91
    eat
    2.64
    <bos>
    2.57
    oos
    2.43
    া
    2.40
    eh
    2.40
    e
    2.35
    త్మ
    2.34
    ze
    2.33
    POSITIVE LOGITS
     InputMaybe
    3.06
    Jlc
    2.97
    ี
    2.95
    setBorder
    2.92
     cristal
    2.88
     MAKEINTRESOURCE
    2.84
    ᱹ
    2.82
     acar
    2.81
    uzzi
    2.81
     scienze
    2.79
    Activations Density 0.000%

    No Known Activations