© 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. 57542
    Prev
    Next
    INDEX
    Explanations

    "tear down" or "close to"

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

    easier, easier, easier, easier

    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
     trava
    0.48
    fro
    0.47
    puma
    0.47
     trabal
    0.45
    or
    0.44
    s
    0.44
    trav
    0.43
     proje
    0.43
     trav
    0.43
     contaminant
    0.42
    POSITIVE LOGITS
     Sacchar
    0.60
    Sug
    0.49
    Stern
    0.49
     تعالیٰ
    0.46
     Sug
    0.45
     textbook
    0.45
    কো
    0.44
    誢
    0.43
    Avg
    0.42
     প্রকার
    0.42
    Activations Density 0.000%

    No Known Activations