© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44890
    Prev
    Next
    INDEX
    Explanations

    packets and

    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_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
     destaca
    0.50
    as
    0.50
    erté
    0.48
     leurs
    0.46
    ారి
    0.45
     diverge
    0.45
    д
    0.44
     tı
    0.44
    өрү
    0.43
    ஈ
    0.43
    POSITIVE LOGITS
     स्थित
    0.42
     વિચારો
    0.41
     Bereiche
    0.41
    rictor
    0.41
    癮
    0.40
    ന്ന്
    0.40
    囟
    0.40
     وح
    0.40
     Bein
    0.40
     بست
    0.40
    Activations Density 0.000%

    No Known Activations