© 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. 112305
    Prev
    Next
    INDEX
    Explanations

    facial expressions, animation, economic

    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
    蔓
    0.46
     መጠቀም
    0.39
     결과를
    0.39
    פ
    0.39
    мо
    0.38
     оши
    0.38
     ಬಳ
    0.38
    瑉
    0.38
    HILL
    0.38
    עת
    0.38
    POSITIVE LOGITS
     commerciales
    0.43
    1
    0.42
     inclusiv
    0.42
     vemos
    0.41
    imea
    0.41
     plenum
    0.41
     konkret
    0.41
     dando
    0.41
     phenomenology
    0.40
     gak
    0.40
    Activations Density 0.004%

    No Known Activations