© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16235
    Prev
    Next
    INDEX
    Explanations

    does not mean or excuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probablement
    0.44
     vre
    0.44
     directement
    0.43
     непосредственно
    0.41
     পুরোপুরি
    0.41
     trud
    0.40
     psicol
    0.40
    |<
    0.39
     పూర్తిగా
    0.39
     অনেকটাই
    0.38
    POSITIVE LOGITS
     nevertheless
    0.61
     doesn
    0.58
     trotzdem
    0.57
     Nevertheless
    0.54
     notwithstanding
    0.52
     означает
    0.52
     Doesn
    0.51
    Doesn
    0.49
    Nevertheless
    0.48
    Does
    0.47
    Activations Density 0.213%

    No Known Activations