© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1018
    Prev
    Next
    INDEX
    Explanations

    requests for action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    —
    2.24
    IRT
    2.09
    —“
    2.05
    --
    2.02
     *(
    2.02
     —
    2.00
    —”
    2.00
    )—
    1.97
    Iowa
    1.96
     *
    1.95
    POSITIVE LOGITS
     advices
    1.49
     equipments
    1.21
     sufferings
    1.18
     upto
    1.06
     freezed
    1.03
     analysing
    1.01
     analyse
    1.00
     analysed
    0.99
     radiations
    0.95
     availed
    0.95
    Activations Density 1.351%

    No Known Activations