© 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. 32969
    Prev
    Next
    INDEX
    Explanations

    cost and time changes

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

    things decreasing over time

    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
     bus
    0.46
     From
    0.45
     た
    0.44
    彼は
    0.44
    驚
    0.44
     Bus
    0.43
     mario
    0.43
     him
    0.42
     .
    0.41
     emerald
    0.41
    POSITIVE LOGITS
    entionally
    0.50
     öffentlich
    0.50
    ahun
    0.49
    politik
    0.49
    uene
    0.48
    otechnical
    0.47
    法语
    0.47
    ocl
    0.46
    investissement
    0.46
    enfance
    0.46
    Activations Density 0.001%

    No Known Activations