© 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. 16-GEMMASCOPE-2-RES-262K
    7. 118357
    Prev
    Next
    INDEX
    Explanations

    above and beyond

    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_16_width_262k_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
     köpek
    0.61
    lägt
    0.58
    ֹ
    0.56
    燜
    0.55
    Ⲱ
    0.55
     Bearded
    0.54
     konstruk
    0.54
    bär
    0.54
     inşa
    0.54
    ärt
    0.53
    POSITIVE LOGITS
     fire
    0.52
     defeat
    0.50
     style
    0.49
     Impulse
    0.48
     Responses
    0.47
     shine
    0.46
     invasions
    0.46
    \
    0.46
    atie
    0.46
    نش
    0.46
    Activations Density 0.000%

    No Known Activations