© 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. 3220
    Prev
    Next
    INDEX
    Explanations

    network troubleshooting

    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
     Ful
    0.66
     genders
    0.59
    枸
    0.59
     Crom
    0.59
    мила
    0.58
     moyennes
    0.57
    ברת
    0.55
    rides
    0.55
     Bor
    0.54
     RX
    0.53
    POSITIVE LOGITS
    얼
    1.40
    Blind
    1.40
    anhyd
    1.38
    ELECT
    1.35
     anhyd
    1.35
    lee
    1.34
    ffi
    1.33
    Rapid
    1.33
    blind
    1.32
     cDNA
    1.32
    Activations Density 0.089%

    No Known Activations