© 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. 149047
    Prev
    Next
    INDEX
    Explanations

    astonishing dreadful appalling

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

    contrasts and limitations

    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
    ]
    0.49
    รอ
    0.48
    (
    0.47
    Corps
    0.45
    タ
    0.44
    ยา
    0.41
    LM
    0.41
    DA
    0.40
    '
    0.40
    Nitro
    0.40
    POSITIVE LOGITS
     disastrous
    0.48
     astonishing
    0.46
     আশ্চর্য
    0.45
     ž
    0.44
     demasi
    0.43
     novelists
    0.42
     heavier
    0.41
     appalling
    0.41
     hitherto
    0.41
     dreadful
    0.41
    Activations Density 0.001%

    No Known Activations