© 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. 154849
    Prev
    Next
    INDEX
    Explanations

    lists and conjunctions

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

    comparing vs alternatives

    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
     Doors
    0.42
     finger
    0.41
     Tester
    0.41
     Debit
    0.40
     Soundtrack
    0.40
     dif
    0.40
     ö
    0.38
     Spy
    0.38
     Tune
    0.38
     Centuries
    0.38
    POSITIVE LOGITS
     និង
    0.53
    ⁾
    0.51
     和
    0.49
    ሲ
    0.48
    ICPSR
    0.48
    pdfs
    0.47
    ៈ
    0.46
    LLY
    0.46
    quers
    0.46
    aeskeygenassist
    0.45
    Activations Density 0.001%

    No Known Activations