© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    Q. A

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

    like, for example, for

    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
    㕝
    0.38
     обл
    0.36
    Ẹ
    0.36
     marginRight
    0.35
     چھ
    0.35
     मार्
    0.35
    を除
    0.35
     nonlinearity
    0.35
     নিয়েছেন
    0.34
    ඝ
    0.34
    POSITIVE LOGITS
    TODO
    0.62
     TODO
    0.61
     blah
    0.59
     ???
    0.58
    blah
    0.56
    foo
    0.55
    ???
    0.53
     somehow
    0.52
    ...?
    0.52
     esempio
    0.51
    Activations Density 0.001%

    No Known Activations