© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4027
    Prev
    Next
    INDEX
    Explanations

    lineage, moon, story

    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
    ソル
    0.90
    Select
    0.90
    h
    0.85
    Func
    0.84
     Sprach
    0.84
     Select
    0.82
    s
    0.80
     Sof
    0.80
     S
    0.80
     Hann
    0.80
    POSITIVE LOGITS
     busted
    1.86
     scorched
    1.83
     ruptured
    1.81
     severed
    1.81
     overhauled
    1.81
     ionized
    1.78
     anomalies
    1.76
     mismanagement
    1.75
     anomaly
    1.73
     rusted
    1.72
    Activations Density 0.069%

    No Known Activations