© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39676
    Prev
    Next
    INDEX
    Explanations

    Cr, Mo, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    those
    -1.53
     auraient
    -1.39
     seraient
    -1.36
     INTERVIEW
    -1.25
     hydrochlor
    -1.24
     clio
    -1.23
     semblent
    -1.20
     wouldn
    -1.20
    other
    -1.19
     norman
    -1.16
    POSITIVE LOGITS
     světa
    1.43
     kierunku
    1.35
     Wissenschaftler
    1.34
     sechs
    1.32
     महत्वपूर्ण
    1.31
     rzeczyw
    1.31
     oczeki
    1.30
     realizacji
    1.30
     trzech
    1.29
     lágrimas
    1.27
    Activations Density 0.052%

    No Known Activations