© 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. 89309
    Prev
    Next
    INDEX
    Explanations

    dumpster rentals and gold CIP

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

    lists introducing capabilities

    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
    DJANGO
    0.47
    Features
    0.45
    Prefs
    0.45
    jekte
    0.42
     tặng
    0.41
    赠
    0.41
    改进
    0.41
    SECURITY
    0.40
    债
    0.40
    Hex
    0.40
    POSITIVE LOGITS
     suspect
    0.48
     інших
    0.46
     obstructing
    0.45
     suspects
    0.44
     testator
    0.44
     fisherman
    0.44
     restraining
    0.44
     amicable
    0.44
     defendant
    0.43
     labourers
    0.43
    Activations Density 0.000%

    No Known Activations