© 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. 98558
    Prev
    Next
    INDEX
    Explanations

    city bus

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

    categories of 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
    km
    0.51
    lord
    0.50
    ure
    0.50
    ubes
    0.47
    =>
    0.47
    orial
    0.46
    ovenant
    0.46
    .')
    0.46
     आवड
    0.45
    )=
    0.45
    POSITIVE LOGITS
    ین
    0.52
    يل
    0.50
    то
    0.49
     гене
    0.47
     انگری
    0.47
     destacado
    0.46
    𝘵
    0.46
    카
    0.45
    กิน
    0.45
    поте
    0.45
    Activations Density 0.000%

    No Known Activations