© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6959
    Prev
    Next
    INDEX
    Explanations

    acids and amino acids

    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_22_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
     Cheltenham
    0.85
     Kla
    0.85
    萧
    0.82
     paral
    0.82
    TPS
    0.82
    昉
    0.82
     Flanagan
    0.81
    銓
    0.80
     Tä
    0.79
    Cas
    0.79
    POSITIVE LOGITS
     acid
    1.65
     Acid
    1.52
    acid
    1.43
     ACID
    1.36
    Acid
    1.34
    酸
    1.33
     acide
    1.31
     axit
    1.30
     anhydride
    1.28
     एसिड
    1.26
    Activations Density 0.095%

    No Known Activations