© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 109147
    Prev
    Next
    INDEX
    Explanations

    | latest | Stoff | Identity | Hagen | samba |

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    <0xB6>
    0.52
    ﮑ
    0.50
     함수의
    0.50
    ва
    0.49
    <0xB5>
    0.49
    換え
    0.48
    на
    0.48
    <0xA6>
    0.47
    代的
    0.46
    ່
    0.46
    POSITIVE LOGITS
    id
    0.61
    s
    0.57
    er
    0.55
    Motor
    0.55
    Scheduler
    0.55
     טוב
    0.55
    City
    0.54
     cidade
    0.54
    For
    0.54
    ant
    0.54
    Activations Density 0.000%

    No Known Activations