© 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. 12312
    Prev
    Next
    INDEX
    Explanations

    identifying riddles

    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
     Discourse
    1.60
     discourse
    1.42
     discourses
    1.38
     DECL
    1.37
    ί
    1.35
     IDENT
    1.31
    ám
    1.31
     DSP
    1.30
     XHTML
    1.29
    랠
    1.26
    POSITIVE LOGITS
     ricordo
    1.43
     ricord
    1.42
     ricordare
    1.42
    গ্রস্থ
    1.40
    кому
    1.38
     অদ্ভুত
    1.37
     uzak
    1.36
     बुन्देलखण्ड
    1.33
     consiglio
    1.33
    centi
    1.31
    Activations Density 0.077%

    No Known Activations