© 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-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 6490
    Prev
    Next
    INDEX
    Explanations

    saving code as a file

    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
    itum
    1.36
    SHIFT
    1.35
     منصوب
    1.34
     positi
    1.34
    istici
    1.30
    }]}
    1.28
    ITY
    1.27
    sick
    1.25
    )*
    1.22
    差点
    1.20
    POSITIVE LOGITS
    aterina
    1.25
    overl
    1.18
     ț
    1.16
    azaki
    1.12
     Searches
    1.10
     encant
    1.10
     trackers
    1.07
    nului
    1.06
     Atlet
    1.06
    uerdo
    1.05
    Activations Density 0.035%

    No Known Activations