© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219136
    Prev
    Next
    INDEX
    Explanations

    differences between, drastic decline

    np_acts-logits-general · gemini-2.5-flash-lite

    risk, latency, developers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     echter
    0.54
     irritate
    0.48
     nebo
    0.47
     mett
    0.47
     biedt
    0.47
     저
    0.46
    stück
    0.46
    to
    0.45
     ljub
    0.45
     eğ
    0.45
    POSITIVE LOGITS
    alakip
    0.49
    ospital
    0.41
     Aufbau
    0.40
    \
    0.40
    㝌
    0.40
     roadway
    0.40
    ifiably
    0.40
     область
    0.39
    urados
    0.39
    妗
    0.39
    Activations Density 0.001%

    No Known Activations