© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    Monster Zone

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

    responds in English

    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
     contabil
    0.44
     achats
    0.42
     zakup
    0.41
    ご注文
    0.40
     statistique
    0.40
     չ
    0.39
     شە
    0.38
     bisnis
    0.38
     juridique
    0.38
    키
    0.38
    POSITIVE LOGITS
     because
    0.42
    因為
    0.40
    porque
    0.40
    because
    0.39
     porque
    0.38
     wegen
    0.37
    abelian
    0.37
    -\\
    0.37
    開啟
    0.37
     omdat
    0.37
    Activations Density 0.000%

    No Known Activations