© 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. 12569
    Prev
    Next
    INDEX
    Explanations

    escaping characters or sequences

    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
    ্ম্ম
    2.96
    ution
    2.84
    ｈ
    2.84
     rectum
    2.82
    ራም
    2.80
    पेश
    2.78
    ባል
    2.76
    aksanakan
    2.66
    鋈
    2.65
    峋
    2.64
    POSITIVE LOGITS
    ই
    2.70
    ן
    2.62
    짚
    2.52
    서
    2.50
    ingham
    2.48
    }+...+\
    2.45
    عرض
    2.42
    besch
    2.36
    서는
    2.34
    ير
    2.29
    Activations Density 0.010%

    No Known Activations