© 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. 7122
    Prev
    Next
    INDEX
    Explanations

    lists of items

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

    concepts and multilingual applications

    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
    }(
    0.22
     including
    0.20
    Также
    0.20
    ().
    0.19
    which
    0.19
     Additionally
    0.19
     considerably
    0.19
     which
    0.19
    以及
    0.19
    ('
    0.18
    POSITIVE LOGITS
     storie
    0.23
    骄
    0.21
     hype
    0.21
     drama
    0.20
     bedrijven
    0.20
    Drama
    0.19
     piz
    0.19
    drama
    0.19
     majesty
    0.19
     preachers
    0.19
    Activations Density 0.492%

    No Known Activations