© 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. 116367
    Prev
    Next
    INDEX
    Explanations

    actions and discoveries

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

    negative consequences or potential

    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
    琰
    0.47
    畊
    0.45
     precisely
    0.44
     sloping
    0.43
     lately
    0.42
    ่า
    0.42
    、
    0.42
     thefe
    0.41
     luckily
    0.41
    பட்ச
    0.41
    POSITIVE LOGITS
     οργαν
    0.53
    ரும
    0.51
    σι
    0.48
    انون
    0.47
     orphanage
    0.46
    sr
    0.46
     Bxb
    0.46
     isomorphism
    0.46
    Ϲ
    0.46
     serum
    0.45
    Activations Density 0.001%

    No Known Activations