© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 16368
    Prev
    Next
    INDEX
    Explanations

    US Iran relations

    np_acts-logits-general · gemini-2.5-flash-lite

    brave, control, surface, often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    로
    0.58
    obes
    0.46
    über
    0.45
    Ons
    0.44
    ions
    0.44
    ),
    0.43
    urón
    0.43
    ONA
    0.42
    ב
    0.42
     हुने
    0.42
    POSITIVE LOGITS
     полити
    0.52
    parvec
    0.51
     új
    0.50
     nagy
    0.50
     அரசியல்
    0.49
     novela
    0.49
     targ
    0.49
     politique
    0.48
     ér
    0.47
     fáj
    0.47
    Activations Density 0.003%

    No Known Activations