© 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. 158081
    Prev
    Next
    INDEX
    Explanations

    current fiscal year

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

    dominant team", "deals", price, head actuators

    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
     unfavorable
    0.50
     कबड्डी
    0.49
    etails
    0.46
    ließ
    0.46
    ließen
    0.46
    })}\
    0.45
    नंतर
    0.45
    addons
    0.44
    et
    0.44
    arrêter
    0.44
    POSITIVE LOGITS
     modo
    0.50
     hame
    0.49
     naz
    0.47
     fais
    0.45
    олові
    0.44
    ном
    0.43
    ɴ
    0.42
     patri
    0.41
     gaya
    0.41
    LEC
    0.41
    Activations Density 0.002%

    No Known Activations