© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1200
    Prev
    Next
    INDEX
    Explanations

    emotional, intellectual, self

    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_13_width_65k_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
    '
    1.06
    :
    1.03
     apenas
    0.91
    Suite
    0.88
     está
    0.86
    ও
    0.85
    Only
    0.84
    "
    0.83
    Le
    0.81
    Then
    0.81
    POSITIVE LOGITS
     interpersonal
    1.35
     교육
    1.34
     responsiveness
    1.34
     motivations
    1.33
    <unused1201>
    1.32
     perceptions
    1.30
     각종
    1.29
     literacy
    1.29
     budgeting
    1.29
     dexterity
    1.29
    Activations Density 1.040%

    No Known Activations