© 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. 203736
    Prev
    Next
    INDEX
    Explanations

    connects, leads to, or involves action

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

    acronym definitions and explanations

    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
     sucht
    0.53
    }}-
    0.49
     lebt
    0.49
     zeigt
    0.48
     sur
    0.48
     steht
    0.48
     registro
    0.48
     zwei
    0.47
     gesam
    0.47
     není
    0.47
    POSITIVE LOGITS
     Adhesive
    0.53
    㠱
    0.52
     adhesives
    0.47
    мад
    0.47
     intruder
    0.47
    raman
    0.46
    ardonnay
    0.45
     contagion
    0.45
    மான
    0.44
    कृष्ण
    0.43
    Activations Density 0.000%

    No Known Activations