© 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. 92143
    Prev
    Next
    INDEX
    Explanations

    peopletreasuresroutehetheys

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

    often see, is when, mimic the, would be

    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
    濫
    0.53
     किराया
    0.51
     Sofia
    0.50
     Garant
    0.50
    Задача
    0.50
    号码
    0.49
     Dord
    0.49
    ത്തേ
    0.49
     Neolithic
    0.49
    oinette
    0.49
    POSITIVE LOGITS
    _
    0.56
     engage
    0.52
     activate
    0.46
    </h2>
    0.44
     dzien
    0.43
    /
    0.43
     becom
    0.43
     troubled
    0.43
     during
    0.42
     onset
    0.42
    Activations Density 0.000%

    No Known Activations