© 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. 124097
    Prev
    Next
    INDEX
    Explanations

    services, tourism, film, challenges

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

    limited budgets or brightness level

    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
     కృషి
    0.52
    𝘦
    0.52
     этом
    0.48
    сида
    0.48
     ڈاک
    0.46
    addena
    0.46
     هڪ
    0.46
     이런
    0.45
    его
    0.44
    }{\
    0.44
    POSITIVE LOGITS
     attractions
    0.45
     interacts
    0.44
     Alsace
    0.43
    +)
    0.43
    gj
    0.41
     is
    0.41
     incidents
    0.41
     jährlich
    0.41
    <footer>
    0.41
     broni
    0.41
    Activations Density 0.003%

    No Known Activations