© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4253
    Prev
    Next
    INDEX
    Explanations

    compliance with, bit small

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Kohn
    1.49
    benzene
    1.34
    덬
    1.32
     Jard
    1.32
    6
    1.29
    8
    1.26
     degrés
    1.26
     ¥
    1.24
     ruhig
    1.22
    type
    1.21
    POSITIVE LOGITS
     envisage
    1.47
     envis
    1.39
     landslide
    1.29
     Drought
    1.18
    確
    1.16
     Migration
    1.15
     ドラ
    1.12
     wid
    1.11
    管道
    1.10
    فى
    1.08
    Activations Density 0.049%

    No Known Activations