© 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-262K
    7. 127169
    Prev
    Next
    INDEX
    Explanations

    models described as smaller

    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
    saraba
    0.51
    uje
    0.49
    Depuis
    0.48
    ნება
    0.47
     বিশেষজ্ঞদের
    0.47
     נמצא
    0.46
    __,
    0.46
     meliputi
    0.46
    바
    0.46
    izados
    0.45
    POSITIVE LOGITS
     panels
    0.46
     conducted
    0.45
     Yankee
    0.44
     backcountry
    0.44
     Giang
    0.44
     seams
    0.43
     paper
    0.43
     bunker
    0.43
     Bankers
    0.41
    য়োজনীয়
    0.40
    Activations Density 0.006%

    No Known Activations