© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2425
    Prev
    Next
    INDEX
    Explanations

    To: phrase start

    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
    7
    1.78
     RQ
    1.68
    q
    1.63
     Bitcoin
    1.62
    Montreal
    1.60
     Kanada
    1.59
     Montreal
    1.58
    6
    1.57
    Canadian
    1.53
     Canada
    1.51
    POSITIVE LOGITS
     witnesses
    0.85
     Witnesses
    0.84
    unteers
    0.84
    力
    0.80
    untes
    0.77
     testimonies
    0.76
     Eust
    0.74
     fortiter
    0.74
     confiance
    0.72
    chst
    0.72
    Activations Density 0.062%

    No Known Activations