© 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. 113702
    Prev
    Next
    INDEX
    Explanations

    child, plastic, attach, event, door

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

    can be suggested

    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
    贲
    0.48
     الدور
    0.47
    icación
    0.46
    ühr
    0.45
    Classe
    0.44
     नूर
    0.44
    Existing
    0.43
    犹如
    0.43
    鸫
    0.42
    🤘
    0.42
    POSITIVE LOGITS
     Sug
    0.46
     suger
    0.45
     alternative
    0.43
     Table
    0.43
     misled
    0.43
     Lemma
    0.42
     subgroups
    0.41
     Suggest
    0.41
     mice
    0.40
     octane
    0.40
    Activations Density 0.000%

    No Known Activations