© 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. 235922
    Prev
    Next
    INDEX
    Explanations

    acabar

    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
    ijas
    0.52
    ahassee
    0.49
     질
    0.47
    aml
    0.46
    anz
    0.46
    iks
    0.46
     सर
    0.46
     태
    0.45
     तळ
    0.45
    ्वा
    0.45
    POSITIVE LOGITS
     acabar
    0.56
     Butch
    0.56
     ServicePolicy
    0.52
     iunie
    0.50
     njegove
    0.49
     Coleoptera
    0.49
    စိတ်
    0.48
     Aprili
    0.48
     seinem
    0.48
    ھوں
    0.48
    Activations Density 0.000%

    No Known Activations