© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10591
    Prev
    Next
    INDEX
    Explanations

    code imports and library usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_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
     मातर
    0.43
     ChangeNotifier
    0.42
    cepat
    0.39
     taill
    0.39
    istert
    0.38
     })();
    0.38
     зам
    0.38
    LongNumber
    0.38
    franz
    0.38
     ensembles
    0.37
    POSITIVE LOGITS
     qualified
    0.48
    QUARE
    0.42
     interactive
    0.41
     aware
    0.39
     injecting
    0.37
    Ğ
    0.37
     requiring
    0.37
    IRS
    0.36
    raseña
    0.36
    PCM
    0.36
    Activations Density 0.042%

    No Known Activations