© 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. 177420
    Prev
    Next
    INDEX
    Explanations

    actions and context

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

    possessive forms and present tense

    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
    榔
    0.50
    ер
    0.49
    eger
    0.47
     sete
    0.46
    THE
    0.46
    加载
    0.45
    RIBE
    0.44
    骄
    0.43
     springer
    0.43
    RUN
    0.43
    POSITIVE LOGITS
     admissibility
    0.45
    〆
    0.44
    apanam
    0.43
     homologs
    0.42
     Bezeichnung
    0.42
     bureaucratic
    0.42
     formalized
    0.42
     approving
    0.42
     piloted
    0.42
     एस
    0.42
    Activations Density 0.001%

    No Known Activations