© 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-16K
    7. 10214
    Prev
    Next
    INDEX
    Explanations

    technical parameters or legal context

    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_16k_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
     r
    0.52
     plato
    0.52
    ?
    0.50
     N
    0.50
    ?'
    0.49
     Inj
    0.48
     pum
    0.48
     For
    0.47
     prized
    0.47
     রস
    0.47
    POSITIVE LOGITS
    𝘏
    0.55
    𝘸
    0.54
    Scaler
    0.49
    ВА
    0.47
    ЗА
    0.46
    Jakarta
    0.46
    𝘞
    0.46
    Synt
    0.45
    EditDialogOpen
    0.45
    Premier
    0.44
    Activations Density 0.022%

    No Known Activations