© 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. 144851
    Prev
    Next
    INDEX
    Explanations

    cannot identify

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

    probability until votes

    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
    ፕ
    0.46
     tampon
    0.45
     interfer
    0.45
    ซ
    0.44
     magnon
    0.44
     lemongrass
    0.44
     Jav
    0.43
     controller
    0.43
     Verified
    0.43
     javac
    0.42
    POSITIVE LOGITS
     বইটি
    0.50
     упо
    0.49
     կ
    0.48
    rité
    0.48
    quist
    0.46
     desconocido
    0.46
    arna
    0.46
    iende
    0.45
    xious
    0.45
    wnie
    0.45
    Activations Density 0.000%

    No Known Activations