© 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. 62389
    Prev
    Next
    INDEX
    Explanations

    author names in references

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

    logical connectors and context

    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
    یط
    0.55
     upholstered
    0.52
     enfrent
    0.51
    넘
    0.49
     aborted
    0.49
    يج
    0.48
     uczniów
    0.48
     inflamed
    0.48
     perpetrated
    0.47
    ął
    0.47
    POSITIVE LOGITS
    globe
    0.51
    rom
    0.50
    love
    0.47
    u
    0.47
    faa
    0.47
    plant
    0.45
    era
    0.44
    ave
    0.44
    stat
    0.43
    family
    0.43
    Activations Density 0.000%

    No Known Activations