© 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. 71495
    Prev
    Next
    INDEX
    Explanations

    low interest, fiberglass doors

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

    describing qualities or styles

    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
    ificateur
    0.52
     grammat
    0.51
    揆
    0.48
    ccgi
    0.46
    ziehungen
    0.45
    ೈನ
    0.45
     увагу
    0.45
    datei
    0.44
    datos
    0.44
    stücke
    0.44
    POSITIVE LOGITS
     wheeled
    0.49
     намного
    0.47
    эл
    0.47
                       
    0.46
     Volleyball
    0.46
     VOL
    0.46
    훨
    0.45
    AGE
    0.45
     thriving
    0.45
    TIMEOUT
    0.44
    Activations Density 0.001%

    No Known Activations