© 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
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 544
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn> dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     calendário
    2.03
    佢
    1.89
     selectors
    1.88
     disampaikan
    1.88
    Councillor
    1.87
    程
    1.86
    etzungen
    1.85
    edian
    1.85
    yrch
    1.83
     (£
    1.82
    POSITIVE LOGITS
     FEEL
    2.26
     базо
    2.17
    8
    2.15
     oliv
    2.14
     потеря
    2.03
     perceive
    2.01
     lugar
    2.01
     почув
    1.99
    7
    1.99
    ˚
    1.97
    Activations Density 0.139%

    No Known Activations