© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8241
    Prev
    Next
    INDEX
    Explanations

    implies, predicts, or focuses on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ^{\
    0.57
     bolje
    0.53
     coleta
    0.52
     muitos
    0.52
     jogadores
    0.52
     pouces
    0.52
     Pokud
    0.51
    <unused694>
    0.51
     annih
    0.51
     novoProduto
    0.50
    POSITIVE LOGITS
    sleep
    0.52
    ழ்
    0.46
     scoop
    0.45
     sleep
    0.44
    ör
    0.44
     Sleep
    0.43
     Recon
    0.43
     New
    0.42
    非
    0.42
     Berlin
    0.41
    Activations Density 0.077%

    No Known Activations