© 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. 145839
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    looking for 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
    neet
    0.52
    ћ
    0.52
    牠
    0.45
     মহাশয়
    0.43
    ਣ
    0.43
    нах
    0.41
    illiams
    0.41
    }^{+
    0.41
     եւ
    0.41
    чку
    0.41
    POSITIVE LOGITS
     imprime
    0.56
     enviados
    0.55
     özel
    0.53
     arque
    0.52
     Özel
    0.52
    m
    0.52
     değiştir
    0.50
     empres
    0.49
     environnement
    0.49
     plena
    0.49
    Activations Density 0.000%

    No Known Activations