© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5969
    Prev
    Next
    INDEX
    Explanations

    world, stories, movies, information, day

    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_12_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
    !;
    1.65
    ,—
    1.64
    ​—
    1.63
     .;
    1.60
    —“
    1.57
    ®,
    1.55
    ™,
    1.55
    "—
    1.51
    ―
    1.47
    、“
    1.46
    POSITIVE LOGITS
     anyways
    2.03
     tbh
    2.02
     fucking
    1.96
     anyway
    1.90
     fucked
    1.80
     shit
    1.80
     stuff
    1.76
     afterwards
    1.71
     ppl
    1.70
     idk
    1.65
    Activations Density 0.292%

    No Known Activations