© 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. 231754
    Prev
    Next
    INDEX
    Explanations

    state levels better

    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
    ة
    0.49
    }):=\
    0.47
     poste
    0.47
     close
    0.46
    ěr
    0.46
     تر
    0.46
     করিয়াছিলেন
    0.45
     данной
    0.45
     verifica
    0.45
     Stevenson
    0.44
    POSITIVE LOGITS
    Feb
    0.49
    Assets
    0.46
    Angles
    0.46
    ᆹ
    0.45
    日本
    0.44
    ബ്
    0.43
     Angles
    0.43
    ٢
    0.43
    ᱒
    0.42
     febru
    0.42
    Activations Density 0.000%

    No Known Activations