© 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. 200810
    Prev
    Next
    INDEX
    Explanations

    animal or streaming or students or screening

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

    digestion, organization, status

    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
     trialComponents
    0.54
    ന്നി
    0.52
    ፫
    0.50
     geworden
    0.50
     şek
    0.49
     sAlarm
    0.48
     Notwithstanding
    0.48
     फोकस
    0.48
    栏
    0.47
     अटेम्प्ट
    0.47
    POSITIVE LOGITS
    اف
    0.48
    violent
    0.46
    ​
    0.44
    ساز
    0.43
     باز
    0.43
    త
    0.43
     reduct
    0.41
    fia
    0.41
     oligarch
    0.41
    อย
    0.40
    Activations Density 0.000%

    No Known Activations