© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1900
    Prev
    Next
    INDEX
    Explanations

    yes, followed by a comma

    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
     (“
    2.65
     (&
    2.54
    (&
    2.37
    ”(
    2.35
     (‘
    2.35
     (#
    2.30
    (!
    2.25
     “(
    2.23
     (~
    2.19
     (!
    2.18
    POSITIVE LOGITS
     ähm
    2.70
     äh
    2.61
     보면은
    2.43
     그다음에
    2.42
     uh
    2.41
     yeah
    2.32
     Mhm
    2.30
     그러면은
    2.29
     Okay
    2.26
     Alright
    2.23
    Activations Density 0.707%

    No Known Activations