© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 51391
    Prev
    Next
    INDEX
    Explanations

    rootkits, selection, carry genes

    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
    مبر
    0.49
     solucionar
    0.47
    னிய
    0.46
    ινων
    0.45
    రు
    0.45
     culoare
    0.44
    द्
    0.43
    庣
    0.43
    玑
    0.43
    мести
    0.43
    POSITIVE LOGITS
    in
    0.58
    cache
    0.55
    ag
    0.55
    le
    0.55
     in
    0.54
     PDF
    0.52
    e
    0.51
    i
    0.51
    scalable
    0.51
    art
    0.50
    Activations Density 0.001%

    No Known Activations