© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8326
    Prev
    Next
    INDEX
    Explanations

    along with

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

    along with

    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_53_width_65k_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
    ח
    0.44
    Ini
    0.39
    Yr
    0.38
    alchemy
    0.38
    গতকাল
    0.38
    ampe
    0.37
     छु
    0.37
    Round
    0.36
    ahl
    0.36
     বিরোধিতা
    0.36
    POSITIVE LOGITS
     along
    0.82
     entlang
    0.70
     вдоль
    0.68
    along
    0.65
    sides
    0.62
    沿
    0.61
     Along
    0.60
     boyunca
    0.59
    side
    0.59
     líneas
    0.57
    Activations Density 0.043%

    No Known Activations