© 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. 12836
    Prev
    Next
    INDEX
    Explanations

    legal and freedom concepts

    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
    <bos>
    2.39
    ت
    2.05
    ન્મ
    2.02
    ох
    1.98
    у
    1.94
    ulers
    1.92
    ing
    1.91
    socks
    1.86
    tre
    1.80
    sis
    1.79
    POSITIVE LOGITS
    nå
    2.30
     &$
    2.25
    ו
    2.19
    ﮏ
    2.10
    AppComponent
    2.10
    ڈا
    1.98
    愎
    1.97
    兒
    1.96
    etzen
    1.92
    inflammatory
    1.91
    Activations Density 0.022%

    No Known Activations