© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7436
    Prev
    Next
    INDEX
    Explanations

    running code instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onboarding
    2.41
     relatable
    2.25
    zk
    2.15
    ѕ
    2.15
    ça
    2.13
     inkl
    2.13
     센터
    2.10
    це
    2.06
     kautta
    2.05
     Shack
    2.02
    POSITIVE LOGITS
    AGUE
    1.80
     AGEN
    1.79
    NDAY
    1.74
    WED
    1.69
    Yesterday
    1.68
    一时
    1.60
    缛
    1.59
     partid
    1.58
    otest
    1.53
    Tomorrow
    1.52
    Activations Density 0.007%

    No Known Activations