© 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. 81395
    Prev
    Next
    INDEX
    Explanations

    not like

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

    support you, align with, no ownership

    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
     நி
    0.53
    APPA
    0.53
    $&$-
    0.52
    িকর
    0.50
     सें
    0.49
    ahuasca
    0.47
     বিক্রি
    0.46
     తి
    0.46
    ichloro
    0.45
    Hướng
    0.44
    POSITIVE LOGITS
    start
    0.48
     honour
    0.46
    class
    0.46
     Hunts
    0.44
     parachute
    0.43
    ੁ
    0.43
     risult
    0.42
     kuid
    0.42
    奋斗
    0.42
     Wills
    0.42
    Activations Density 0.000%

    No Known Activations