© 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. 187715
    Prev
    Next
    INDEX
    Explanations

    agave nectar

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

    writing constrained text

    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
    वेत
    0.44
    ό
    0.44
     nghệ
    0.42
    笙
    0.42
     liées
    0.41
    ӣ
    0.41
    ógrafo
    0.41
    ά
    0.40
    ῖ
    0.40
     сю
    0.40
    POSITIVE LOGITS
     hass
    0.50
     tablespoon
    0.48
     tablespoons
    0.46
     hypothyroidism
    0.45
     compartments
    0.45
     oppressed
    0.42
     shackles
    0.42
     pancakes
    0.42
     hyp
    0.41
     handcuffs
    0.41
    Activations Density 0.000%

    No Known Activations