© 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. 651
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline

    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
     the
    0.73
    :
    0.63
     a
    0.55
    -
    0.54
     no
    0.53
     all
    0.52
     c
    0.51
    0.50
      
    0.50
     two
    0.49
    POSITIVE LOGITS
    commonByteArray
    1.27
    𒀠
    1.27
    𒄖
    1.26
    𒈤
    1.26
    𒌐
    1.26
    <unused1500>
    1.26
    𒈪
    1.25
    𒀫
    1.25
    𒉪
    1.25
    𒌜
    1.25
    Activations Density 0.660%

    No Known Activations