© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10595
    Prev
    Next
    INDEX
    Explanations

    RAINN (Rape, Abuse & Incest National Network)

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

    The neuron activates on uppercase multi-letter acronyms or initialisms (all-caps sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    }
    0.87
    ist
    0.86
     lateribus
    0.85
     carinatis
    0.84
    deux
    0.80
     embryonic
    0.79
    ophil
    0.79
     memoirs
    0.78
    TURN
    0.77
     mikä
    0.77
    POSITIVE LOGITS
    نید
    0.99
    ﻭ
    0.98
    و
    0.97
    ن
    0.97
     Rental
    0.96
    ん
    0.96
    sby
    0.93
    ி
    0.93
    i
    0.93
    ל
    0.93
    Activations Density 0.000%

    No Known Activations