© 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. 151596
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    technical explanations with formatting

    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
    ü
    0.49
     mooi
    0.48
     schön
    0.47
     schade
    0.47
     allez
    0.46
    ants
    0.46
     retard
    0.45
    å
    0.45
     ii
    0.44
     necrosis
    0.44
    POSITIVE LOGITS
     purportedly
    0.46
     ostensibly
    0.43
     Disbursement
    0.42
    মুখী
    0.41
    azón
    0.41
     வலியுறு
    0.40
     Aziz
    0.40
     noviembre
    0.40
     unprecedented
    0.39
    才能
    0.39
    Activations Density 0.000%

    No Known Activations