© 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. 52192
    Prev
    Next
    INDEX
    Explanations

    exclamations!

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

    ending questions

    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
    There
    0.44
     Ciencia
    0.44
    If
    0.42
     Örneğin
    0.41
     There
    0.41
    The
    0.40
    ----------------
    0.40
     Emotional
    0.39
     Informasi
    0.39
     If
    0.38
    POSITIVE LOGITS
     frameworks
    0.46
    ুরি
    0.44
     也
    0.44
     renderEncoder
    0.43
     aswell
    0.42
     snugly
    0.41
     以及
    0.41
     vaults
    0.39
     postures
    0.39
     frames
    0.39
    Activations Density 0.022%

    No Known Activations