© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12386
    Prev
    Next
    INDEX
    Explanations

    multi-lingual tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    𝗶
    2.40
    prec
    2.38
    ية
    2.30
    ing
    2.29
    ᅣ
    2.24
    թ
    2.20
    ities
    2.19
    метка
    2.17
    萠
    2.16
    )':
    2.14
    POSITIVE LOGITS
    здат
    2.69
     ContentView
    2.61
    ovní
    2.59
    ﻞ
    2.59
    व्र
    2.56
    nosť
    2.56
    ratulations
    2.53
    inuous
    2.51
    ︠
    2.47
    えます
    2.44
    Activations Density 0.014%

    No Known Activations