© 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. 246522
    Prev
    Next
    INDEX
    Explanations

    provide for multiple

    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
    :");
    0.58
     množ
    0.56
    mehndi
    0.56
     tumeurs
    0.55
    igenschaften
    0.55
     pohon
    0.54
     hôtels
    0.54
     iccad
    0.53
     цены
    0.53
     étamines
    0.53
    POSITIVE LOGITS
     Statistic
    0.55
     March
    0.54
     Year
    0.53
     Solvent
    0.53
     Health
    0.50
    ↵↵
    0.50
     December
    0.49
     Environmental
    0.49
     Measuring
    0.48
     Toast
    0.48
    Activations Density 0.000%

    No Known Activations