© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 4212
    Prev
    Next
    INDEX
    Explanations

    login, ready, company, reflect, Echo, modules

    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
     both
    2.41
     one
    2.38
     organisation
    1.88
     evidence
    1.76
    蜊
    1.73
     One
    1.70
     her
    1.67
     schemes
    1.66
     of
    1.61
     other
    1.59
    POSITIVE LOGITS
    7
    3.79
    rinsic
    3.69
    6
    3.58
    8
    3.55
    5
    3.41
    ️⃣
    3.39
    4
    3.34
    0
    3.27
     akademik
    3.18
    9
    3.13
    Activations Density 0.134%

    No Known Activations