© 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. 21690
    Prev
    Next
    INDEX
    Explanations

    How and love statements

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

    programming conditional checks

    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
    脨
    0.42
    三個
    0.40
    㞒
    0.40
    ドレス
    0.38
     तीन
    0.38
    गील
    0.37
     hasilnya
    0.37
     hilang
    0.37
    の中で
    0.36
    迭
    0.35
    POSITIVE LOGITS
    ation
    0.42
    ate
    0.41
    !
    0.38
    ="
    0.37
     is
    0.36
    ='
    0.36
    rus
    0.36
    ind
    0.35
                       
    0.35
    ato
    0.35
    Activations Density 0.009%

    No Known Activations