© 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. 162774
    Prev
    Next
    INDEX
    Explanations

    compound words and names

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

    code and technical terms

    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
     )
    0.43
     HOA
    0.42
     KR
    0.40
    вам
    0.40
     Branson
    0.39
     K
    0.39
     DA
    0.39
    มห
    0.38
     HO
    0.38
     entschied
    0.38
    POSITIVE LOGITS
    રોના
    0.50
    ৬৮
    0.46
    غير
    0.46
     غیر
    0.45
    शिवाय
    0.45
    defe
    0.44
    voltage
    0.44
    uvieron
    0.43
    profession
    0.42
    Además
    0.42
    Activations Density 0.367%

    No Known Activations