© 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. 137887
    Prev
    Next
    INDEX
    Explanations

    illnesses, office, or groups

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

    programming math includes

    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
     चाहता
    0.45
    助
    0.45
    acti
    0.44
    Der
    0.43
    尷
    0.43
    我们可以
    0.43
    eeper
    0.41
    岩
    0.41
     помогает
    0.40
    可以让
    0.40
    POSITIVE LOGITS
     quedan
    0.47
     nichts
    0.45
     EtOH
    0.45
     siano
    0.44
     budou
    0.44
     prestar
    0.43
     vivir
    0.42
     diagnose
    0.42
     léz
    0.42
     bunyi
    0.42
    Activations Density 0.000%

    No Known Activations