© 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. 175872
    Prev
    Next
    INDEX
    Explanations

    what others think

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

    what others think

    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
     cần
    0.51
     perlu
    0.46
     ya
    0.46
    akses
    0.45
     właścic
    0.44
    迺
    0.44
    ٹس
    0.43
     yakin
    0.43
    </em>
    0.42
     candidat
    0.42
    POSITIVE LOGITS
     murmured
    0.40
    基督教
    0.39
    ය
    0.39
     decreed
    0.39
     readjust
    0.38
    面上
    0.38
     срав
    0.37
     கண
    0.37
     comedies
    0.36
     खूब
    0.36
    Activations Density 0.005%

    No Known Activations