© 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-65K
    7. 29000
    Prev
    Next
    INDEX
    Explanations

    sun size and comparisons

    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
    df
    0.46
     ($
    0.46
    ach
    0.45
     calves
    0.45
     αρ
    0.45
     ocorrer
    0.45
     (@
    0.44
    áticamente
    0.42
    calf
    0.42
    နာ
    0.42
    POSITIVE LOGITS
    шно
    0.51
     microseconds
    0.49
     때문
    0.47
     terminals
    0.47
     تقسيم
    0.45
    NUM
    0.45
    गृह
    0.45
    قسم
    0.45
    泾
    0.45
    ygons
    0.44
    Activations Density 0.010%

    No Known Activations