© 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. 158500
    Prev
    Next
    INDEX
    Explanations

    encaustic paintings, encapsulants, direct dyes

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

    remember that real

    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
    กอง
    0.47
    இந்நிலையில்
    0.45
    협
    0.45
    <unused23>
    0.43
     všech
    0.43
    adă
    0.42
     যতদিন
    0.42
    Spawn
    0.41
    <unused76>
    0.41
    eszcze
    0.41
    POSITIVE LOGITS
     textura
    0.45
     seri
    0.43
     call
    0.43
     calc
    0.43
     washed
    0.41
     can
    0.41
     Texture
    0.41
     back
    0.39
     din
    0.39
     modeled
    0.39
    Activations Density 0.000%

    No Known Activations