© 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. 114497
    Prev
    Next
    INDEX
    Explanations

    historical contexts and states

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

    sequential data processing

    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
    and
    0.46
    &&\
    0.43
    昆
    0.43
    和
    0.42
    ו
    0.41
    NL
    0.41
    魷
    0.41
    IL
    0.40
    PEP
    0.40
    AT
    0.40
    POSITIVE LOGITS
    𝒔
    0.51
     Were
    0.46
     moulded
    0.46
     hapless
    0.45
    èses
    0.45
     Buildings
    0.45
     edificios
    0.45
     WERE
    0.44
    ভেজ
    0.44
    üdis
    0.44
    Activations Density 0.000%

    No Known Activations