© 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. 143118
    Prev
    Next
    INDEX
    Explanations

    iOS, months, evolved, Olsen, Concerns, instances

    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
    ובה
    0.50
    ене
    0.50
    f
    0.48
    ול
    0.47
    έργ
    0.46
    াণ
    0.45
    ificante
    0.45
     fictitious
    0.44
    uala
    0.44
    בד
    0.44
    POSITIVE LOGITS
    Mathematics
    0.47
    Medit
    0.43
    Col
    0.41
    Shopping
    0.40
    Nurse
    0.40
     discoveries
    0.40
     ideas
    0.40
    Ti
    0.40
    °
    0.40
    SignIn
    0.39
    Activations Density 0.001%

    No Known Activations