© 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. 102390
    Prev
    Next
    INDEX
    Explanations

    introduction of descriptive or defining words

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

    certifications, company, trained, care, trauma

    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
    Tras
    0.46
    of
    0.43
    }"]
    0.43
    }{{
    0.43
    ","
    0.42
    otros
    0.42
     {
    0.41
    ಾಪ
    0.41
     .
    0.41
    ᄆ
    0.41
    POSITIVE LOGITS
    ッジ
    0.52
    睑
    0.52
     Defaults
    0.50
    偪
    0.46
    氲
    0.46
     kalem
    0.46
    મ્
    0.46
    seekBar
    0.46
     carénés
    0.45
     Beschreibung
    0.45
    Activations Density 0.001%

    No Known Activations