© 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. 12720
    Prev
    Next
    INDEX
    Explanations

    landed, land on

    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
    Pre
    2.10
    PRE
    2.02
     Pre
    2.02
    pre
    1.99
    பூ
    1.93
    Ọ
    1.88
    カリ
    1.87
    ই
    1.85
    مر
    1.73
     pre
    1.73
    POSITIVE LOGITS
    omania
    2.35
    @[+][
    2.33
    hemian
    2.30
     eyeglasses
    2.26
    igat
    2.20
     earners
    2.20
    िएको
    2.17
     tubs
    2.16
     commutative
    2.16
    មើ
    2.14
    Activations Density 0.001%

    No Known Activations