© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19240
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and clauses

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     AND
    0.45
     melanjutkan
    0.40
     and
    0.39
     continuing
    0.39
     More
    0.38
    <h3>
    0.38
     FMC
    0.36
     MORE
    0.36
     Visit
    0.36
     AMD
    0.36
    POSITIVE LOGITS
    𝗂
    0.49
    acée
    0.48
    劷
    0.48
    lepší
    0.48
     myFunction
    0.47
     ہوسک
    0.46
     inactivació
    0.46
    答应
    0.45
    द्योगिक
    0.44
     editText
    0.44
    Activations Density 0.000%

    No Known Activations