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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 807
    Prev
    Next
    INDEX
    Explanations

    again very common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čních
    0.89
    écran
    0.88
    '
    0.87
    Objet
    0.85
    Ako
    0.84
    ljanje
    0.83
    atience
    0.81
    Votre
    0.79
    </
    0.78
    eine
    0.78
    POSITIVE LOGITS
     From
    0.91
     sixties
    0.90
    ্রাজ
    0.88
     wealthy
    0.88
     chalc
    0.87
     plains
    0.86
     overgrown
    0.85
     older
    0.84
     padre
    0.84
     names
    0.83
    Activations Density 0.967%

    No Known Activations