© 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. 37161
    Prev
    Next
    INDEX
    Explanations

    your marketing

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

    topics and categories

    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
    </h4>
    0.49
     食
    0.47
     सुप्रभात
    0.44
    放入
    0.44
     дисци
    0.43
    सूर
    0.43
     HC
    0.43
     優
    0.42
     استعمال
    0.42
    "/"
    0.42
    POSITIVE LOGITS
     candidats
    0.50
     proprement
    0.46
    یں
    0.46
     changement
    0.46
     desgaste
    0.45
     pobreza
    0.45
     spins
    0.45
    meV
    0.45
     violência
    0.44
    降り
    0.44
    Activations Density 0.000%

    No Known Activations