© 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. 227848
    Prev
    Next
    INDEX
    Explanations

    drove into, different payoffs, financial trouble

    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
    ماش
    0.54
    tileSize
    0.54
    Tod
    0.53
    諡
    0.53
    խ
    0.52
    谥
    0.52
    ἓ
    0.51
    
    0.51
    ۇر
    0.49
    
    0.49
    POSITIVE LOGITS
     pull
    0.54
     café
    0.47
     Pull
    0.46
     GPS
    0.46
     fatti
    0.46
     pullback
    0.46
     skit
    0.45
     wrap
    0.45
     พร้อม
    0.45
     convo
    0.45
    Activations Density 0.000%

    No Known Activations