© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11981
    Prev
    Next
    INDEX
    Explanations

    the descriptor "soft"

    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
    ي
    3.80
    اا
    3.35
    ا
    3.33
    eeee
    3.17
    eee
    3.02
    ્ઞ
    2.92
     ascribed
    2.88
    ীয়
    2.80
    اوی
    2.72
    髦
    2.70
    POSITIVE LOGITS
    ility
    2.43
    ра
    2.42
    轫
    2.40
    
    2.37
    raz
    2.35
    res
    2.35
    ради
    2.34
    ৈতিক
    2.34
    Datei
    2.32
    말
    2.27
    Activations Density 0.017%

    No Known Activations