© 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. 73464
    Prev
    Next
    INDEX
    Explanations

    slot

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

    reminder or request for information

    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
     півні
    0.63
    Ợ
    0.53
     huynh
    0.51
    AMENTE
    0.51
     chuột
    0.50
     incênd
    0.49
     Eğ
    0.49
     !"
    0.48
    GÁ
    0.47
    ILERS
    0.47
    POSITIVE LOGITS
    putExtra
    0.45
    {{
    0.43
    physical
    0.42
     Kennedy
    0.42
    astrophe
    0.41
    state
    0.41
    getElementsBy
    0.41
    しば
    0.41
    보면
    0.41
    ene
    0.41
    Activations Density 0.000%

    No Known Activations