© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6441
    Prev
    Next
    INDEX
    Explanations

    handling network responses

    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_15_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
    kou
    1.55
    UNLOCK
    1.52
    herjee
    1.50
     biotechn
    1.47
    禮
    1.46
     monic
    1.43
    invariant
    1.42
    asures
    1.40
    度和
    1.40
    볕
    1.40
    POSITIVE LOGITS
     mAh
    1.21
     pq
    1.20
     betyd
    1.14
    aterra
    1.13
     pemas
    1.12
     Wedgwood
    1.12
     betre
    1.10
     taim
    1.09
     expliqué
    1.09
    ıcı
    1.08
    Activations Density 0.016%

    No Known Activations