© 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. 247711
    Prev
    Next
    INDEX
    Explanations

    | Comments

    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
     cocinar
    0.51
     acompañado
    0.45
     amplo
    0.42
     estilos
    0.42
    <0xA0>
    0.42
     amplio
    0.42
     добав
    0.41
    ହ
    0.41
     actúa
    0.40
     fryer
    0.40
    POSITIVE LOGITS
    以上に
    0.47
    在新
    0.46
     குறு
    0.45
     $\
    0.44
     $>
    0.43
    ollow
    0.43
     이상의
    0.42
    途
    0.42
     مدیر
    0.42
    pecific
    0.42
    Activations Density 0.001%

    No Known Activations