© 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. 157367
    Prev
    Next
    INDEX
    Explanations

    Amazon Com, market dynamics, the West, the UK

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

    prepositional phrases and descriptions

    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
    なんだ
    0.49
    お子
    0.46
     assertThat
    0.45
    ोर्ट
    0.44
     milion
    0.44
    警方
    0.43
    够
    0.43
     neler
    0.42
    慎
    0.42
    的作品
    0.42
    POSITIVE LOGITS
    ÍA
    0.46
    ía
    0.45
     francés
    0.44
    conference
    0.44
     interfacing
    0.44
    Furn
    0.43
     prohibiting
    0.43
    ễn
    0.43
     indistinct
    0.43
    threat
    0.42
    Activations Density 0.000%

    No Known Activations