© 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. 197298
    Prev
    Next
    INDEX
    Explanations

    booked taxis, optionally accept

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

    after noon or not

    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
     lanz
    0.51
    ]")
    0.50
    ancial
    0.50
     見
    0.47
     complejo
    0.47
    REY
    0.46
    ]=
    0.46
     sano
    0.46
     був
    0.46
    𝐼
    0.45
    POSITIVE LOGITS
    eldo
    0.45
     ”,
    0.44
    Sf
    0.44
    asjon
    0.43
     हमसे
    0.43
     Kirst
    0.43
    োপ
    0.42
     *,
    0.41
    گە
    0.41
    öra
    0.41
    Activations Density 0.000%

    No Known Activations