© 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. 99796
    Prev
    Next
    INDEX
    Explanations

    joint bilingual

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

    discussion about missing IM/DB elements

    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
    💏
    0.49
    ρη
    0.48
    င့်
    0.47
    utacji
    0.46
    ောင့်
    0.46
    वता
    0.45
    ടുത്തു
    0.45
    '_{\
    0.45
    ποιη
    0.45
    ngthening
    0.44
    POSITIVE LOGITS
    现场
    0.49
    ?=
    0.43
    짬
    0.43
    ニュー
    0.42
    症
    0.42
     Tropical
    0.42
     Städte
    0.42
    ASP
    0.41
     Asian
    0.41
    或者是
    0.41
    Activations Density 0.001%

    No Known Activations