© 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. 178042
    Prev
    Next
    INDEX
    Explanations

    dumpster rentals

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

    companies, islands, evolution, physics

    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
     heroic
    0.52
     воз
    0.48
     hysterical
    0.48
     chival
    0.47
     כ
    0.47
     screenings
    0.46
    ത്തിക
    0.46
     เรียน
    0.46
     carcinogenic
    0.45
     tetanus
    0.45
    POSITIVE LOGITS
     Dems
    0.49
     Spicy
    0.48
     Maynard
    0.48
     Sure
    0.47
     Hayes
    0.46
     Moves
    0.45
    qr
    0.45
    不易
    0.45
    Ї
    0.45
     Evolution
    0.44
    Activations Density 0.001%

    No Known Activations