© 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. 123275
    Prev
    Next
    INDEX
    Explanations

    just a + descriptor

    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
     it
    0.49
     Frankly
    0.44
     Alhamdulillah
    0.44
     Needless
    0.43
    ت
    0.42
    虚
    0.42
     bliver
    0.42
     अधिवेशन
    0.42
     inclement
    0.41
     tighten
    0.41
    POSITIVE LOGITS
    rando
    0.48
    곳
    0.46
    ге
    0.46
    Geo
    0.46
     guardia
    0.44
    infodisc
    0.44
    undo
    0.44
     หา
    0.44
     proposé
    0.43
     estimés
    0.43
    Activations Density 0.005%

    No Known Activations