© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3383
    Prev
    Next
    INDEX
    Explanations

    early detection

    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
    ing
    4.22
    ت
    3.54
    ہ
    3.44
    た
    3.41
    roads
    3.30
    𝓹
    3.11
    いたら
    3.11
    osoma
    3.08
    ା
    3.07
    ed
    3.07
    POSITIVE LOGITS
    stateMutability
    3.46
    tti
    3.43
    ઓ
    3.22
    नियर
    3.05
    dır
    3.05
    Jlc
    3.05
    瀣
    3.05
    꾼
    3.01
    बीएसई
    2.99
    ndor
    2.98
    Activations Density 0.021%

    No Known Activations