© 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-65K
    4. 49401
    Prev
    Next
    INDEX
    Explanations

    flexible phrasing or options

    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_65k_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
     انه
    0.43
     position
    0.42
     NPV
    0.42
     GeV
    0.42
    Jogo
    0.42
     place
    0.41
    '
    0.41
     vegetarian
    0.40
     DIN
    0.40
     ERP
    0.40
    POSITIVE LOGITS
    hamton
    0.56
     साकार
    0.51
     ту
    0.48
    력을
    0.48
    투
    0.47
    ową
    0.46
     memudahkan
    0.46
     soybeans
    0.46
     худо
    0.46
    구성
    0.45
    Activations Density 0.005%

    No Known Activations