Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8153
    Prev
    Next
    INDEX
    Explanations

    get, verify, or new

    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_31_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
                     
    0.36
    </ul>
    0.35
     Ont
    0.35
     
    0.34
     Jonathan
    0.34
     countered
    0.34
    ပါတယ်။
    0.34
     bela
    0.34
     অনেকটা
    0.34
     Stéph
    0.34
    POSITIVE LOGITS
    get
    0.48
    normalization
    0.41
    ה
    0.40
    erro
    0.40
    анали
    0.39
    uradaki
    0.39
    መሪያ
    0.39
     fejl
    0.39
     করিয়াছিল
    0.38
    գ
    0.38
    Activations Density 0.004%

    No Known Activations